karl/searchi
1
0 Fork 0
Code Issues Pull Requests Packages Projects Releases 10 Wiki Activity
Files
aca0a0a4ce26924faf1513fc195dbef6e778da58
searchi/fixtures/media/pipeline-10s-results.json
T
karl b8400c4fbf
Core CI / core (ubuntu-latest) (push) Failing after 3m31s
Core CI / core (macos-latest) (push) Canceled after 0s
Core CI / core (windows-latest) (push) Canceled after 0s
Core CI / desktop (ubuntu-latest) (push) Successful in 5m39s
Core CI / desktop (macos-latest) (push) Canceled after 0s
Core CI / desktop (windows-latest) (push) Canceled after 0s
feat: add multimodal search and granular performance diagnostics
2026-10-12 19:16:23 +02:00

22540 lines
630 KiB
JSON
Raw Blame History

{
"audio_overlap_ms": 2000,
"audio_window_ms": 10000,
"encoding_failures": [],
"encoding_ms": 671510.0948000001,
"filename_index": {
"discovered": 20,
"failures": 0,
"indexed": 20,
"removed": 0,
"skipped": 20,
"unchanged": 0
},
"fixture_sha256": "b4e465a0eb9582b826eebd2a20797e1680e4907e336d02d0ef2194e2ba0af393",
"index_report": {
"chunks": 154,
"failures": [],
"generation": 1,
"media_failures": 0,
"media_files": 20,
"model_fingerprint": "google/embeddinggemma-2:bfcd298762cc34d0357ece5ebdd31791a3a374d8:q8_0:llama-b11461-no-logits-v1:mean:l2:query512:doc2048:windows-overlap128:prompts-v1:byte64k-overlap512-title512-v1:google/embeddinggemma-2:bfcd298762cc34d0357ece5ebdd31791a3a374d8:q8_0:llama-b11461-no-logits-v1:mtmd:mean:l2:rgb-catmullrom48-exif-largejpeg-scaled-v2:pcm16k30s-v1:image280-frame70-audio30s-overlap2-distributed240-scene120-v1:custom-240-2000-120-10000-2000-600-14400000-17179869184",
"passages": 0
},
"rows": [
{
"file_rankings": [
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 12.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 10000
},
"start_s": 10.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image01"
],
"hard_negatives": [],
"id": "q001",
"language": "en",
"text": "the fluffy striped cat resting with its chin on the floor"
},
"query_ms": 94.13820000000001,
"segment_top5": [
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 12.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 10000
},
"start_s": 10.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 12.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 10000
},
"start_s": 10.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image01"
],
"hard_negatives": [],
"id": "q002",
"language": "de",
"text": "die flauschige gestreifte Katze liegt mit dem Kinn auf dem Boden"
},
"query_ms": 119.73100000000001,
"segment_top5": [
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 12.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 10000
},
"start_s": 10.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image02"
],
"hard_negatives": [
"image09"
],
"id": "q003",
"language": "en",
"text": "the overhead breakfast bowl with berries and diced mango"
},
"query_ms": 90.447,
"segment_top5": [
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip02",
"end_s": 2.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image02"
],
"hard_negatives": [
"image09"
],
"id": "q004",
"language": "de",
"text": "die Frühstücksschüssel mit Beeren und gewürfelter Mango von oben"
},
"query_ms": 112.2064,
"segment_top5": [
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image03"
],
"hard_negatives": [
"image05",
"image06",
"image04"
],
"id": "q005",
"language": "en",
"text": "the daytime lake reflecting jagged mountains and pine trees"
},
"query_ms": 86.0642,
"segment_top5": [
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image03"
],
"hard_negatives": [
"image05",
"image06",
"image04"
],
"id": "q006",
"language": "de",
"text": "der See bei Tageslicht spiegelt schroffe Berge und Tannen"
},
"query_ms": 106.8406,
"segment_top5": [
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 13320
},
"start_s": 13.32
},
"score": 0.015625
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image04"
],
"hard_negatives": [],
"id": "q007",
"language": "en",
"text": "the Milky Way over a dark mountain valley"
},
"query_ms": 81.38969999999999,
"segment_top5": [
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 13320
},
"start_s": 13.32
},
"score": 0.015625
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 13320
},
"start_s": 13.32
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image04"
],
"hard_negatives": [],
"id": "q008",
"language": "de",
"text": "die Milchstraße über einem dunklen Bergtal"
},
"query_ms": 88.7739,
"segment_top5": [
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 13320
},
"start_s": 13.32
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image05"
],
"hard_negatives": [
"image03",
"image04"
],
"id": "q009",
"language": "en",
"text": "the wooden jetty pointing into a lake under moonlight"
},
"query_ms": 85.09859999999999,
"segment_top5": [
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image05"
],
"hard_negatives": [
"image03",
"image04"
],
"id": "q010",
"language": "de",
"text": "der Holzsteg führt bei Mondlicht in einen See"
},
"query_ms": 93.1671,
"segment_top5": [
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 13320
},
"start_s": 13.32
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image06"
],
"hard_negatives": [],
"id": "q011",
"language": "en",
"text": "the pink layered mountain ridges beneath a golden sunset"
},
"query_ms": 90.7512,
"segment_top5": [
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 72.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 70000
},
"start_s": 70.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip02",
"end_s": 2.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image06"
],
"hard_negatives": [],
"id": "q012",
"language": "de",
"text": "die rosa Bergketten unter einem goldenen Sonnenuntergang"
},
"query_ms": 97.4549,
"segment_top5": [
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 72.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 70000
},
"start_s": 70.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip02",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image07"
],
"hard_negatives": [],
"id": "q013",
"language": "en",
"text": "the herd of cows on green hills"
},
"query_ms": 83.59179999999999,
"segment_top5": [
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip02",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image07"
],
"hard_negatives": [],
"id": "q014",
"language": "de",
"text": "die Kuhherde auf grünen Hügeln"
},
"query_ms": 100.5504,
"segment_top5": [
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 28.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 26000
},
"start_s": 26.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image08"
],
"hard_negatives": [],
"id": "q015",
"language": "en",
"text": "the red sports car driving through woods"
},
"query_ms": 77.5883,
"segment_top5": [
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 28.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 26000
},
"start_s": 26.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 28.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 26000
},
"start_s": 26.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image08"
],
"hard_negatives": [],
"id": "q016",
"language": "de",
"text": "das rote Sportauto fährt durch den Wald"
},
"query_ms": 81.0907,
"segment_top5": [
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 28.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 26000
},
"start_s": 26.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "music02",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image09"
],
"hard_negatives": [
"image02"
],
"id": "q017",
"language": "en",
"text": "the vegetable and grain bowl beside carrot slices"
},
"query_ms": 92.08879999999999,
"segment_top5": [
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image09"
],
"hard_negatives": [
"image02"
],
"id": "q018",
"language": "de",
"text": "die Gemüse-Getreide-Schüssel neben Karottenscheiben"
},
"query_ms": 110.4152,
"segment_top5": [
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image10"
],
"hard_negatives": [],
"id": "q019",
"language": "en",
"text": "milk being poured into coffee to make a pattern"
},
"query_ms": 83.9215,
"segment_top5": [
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image10"
],
"hard_negatives": [],
"id": "q020",
"language": "de",
"text": "Milch wird für ein Muster in den Kaffee gegossen"
},
"query_ms": 91.7982,
"segment_top5": [
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 22.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 20000
},
"start_s": 20.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image11"
],
"hard_negatives": [],
"id": "q021",
"language": "en",
"text": "the empty tropical beach with turquoise water"
},
"query_ms": 77.24499999999999,
"segment_top5": [
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 22.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 20000
},
"start_s": 20.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "clip03",
"end_s": 2.003,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 3
},
"start_s": 0.003
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image11"
],
"hard_negatives": [],
"id": "q022",
"language": "de",
"text": "der leere tropische Strand mit türkisfarbenem Wasser"
},
"query_ms": 100.953,
"segment_top5": [
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image12"
],
"hard_negatives": [],
"id": "q023",
"language": "en",
"text": "the black and white photo with a hand reaching towards us"
},
"query_ms": 92.7337,
"segment_top5": [
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 10.333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8333
},
"start_s": 8.333
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "image-memory",
"expected": [
"image12"
],
"hard_negatives": [],
"id": "q024",
"language": "de",
"text": "das Schwarzweißfoto mit einer Hand, die nach uns greift"
},
"query_ms": 102.18339999999999,
"segment_top5": [
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 10.333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8333
},
"start_s": 8.333
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 14.467,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 12467
},
"start_s": 12.467
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-action",
"expected": [
"clip01"
],
"hard_negatives": [
"image01"
],
"id": "q025",
"intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
},
"language": "en",
"negative_intervals": {
"clip01": [
[
7,
14
]
]
},
"text": "the cat jumping up beside a door handle"
},
"query_ms": 83.2504,
"segment_top5": [
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 14.467,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 12467
},
"start_s": 12.467
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-action",
"expected": [
"clip01"
],
"hard_negatives": [
"image01"
],
"id": "q026",
"intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
},
"language": "de",
"negative_intervals": {
"clip01": [
[
7,
14
]
]
},
"text": "die Katze springt neben dem Türgriff hoch"
},
"query_ms": 97.1897,
"segment_top5": [
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-action",
"expected": [
"clip01"
],
"id": "q027",
"intervals": {
"clip01": [
[
7,
14
]
]
},
"language": "en",
"negative_intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
},
"text": "the cat sitting low by the door after trying to open it"
},
"query_ms": 102.03750000000001,
"segment_top5": [
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-action",
"expected": [
"clip01"
],
"id": "q028",
"intervals": {
"clip01": [
[
7,
14
]
]
},
"language": "de",
"negative_intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
},
"text": "die Katze sitzt nach dem Öffnungsversuch unten an der Tür"
},
"query_ms": 105.6104,
"segment_top5": [
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-temporal",
"expected": [
"clip03"
],
"id": "q029",
"intervals": {
"clip03": [
[
0,
1.0
]
]
},
"language": "en",
"negative_intervals": {
"clip03": [
[
3.5,
5.05
]
]
},
"text": "the red flower bud before its petals open"
},
"query_ms": 87.25489999999999,
"segment_top5": [
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-temporal",
"expected": [
"clip03"
],
"id": "q030",
"intervals": {
"clip03": [
[
0,
1.0
]
]
},
"language": "de",
"negative_intervals": {
"clip03": [
[
3.5,
5.05
]
]
},
"text": "die rote Blütenknospe bevor sich die Blätter öffnen"
},
"query_ms": 101.0436,
"segment_top5": [
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 4.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2000
},
"start_s": 2.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 79000
},
"start_s": 79.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-temporal",
"expected": [
"clip03"
],
"id": "q031",
"intervals": {
"clip03": [
[
3.5,
5.05
]
]
},
"language": "en",
"negative_intervals": {
"clip03": [
[
0,
1.0
]
]
},
"text": "the red flower with its petals open wide"
},
"query_ms": 84.4982,
"segment_top5": [
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 79000
},
"start_s": 79.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 79000
},
"start_s": 79.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip01",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-temporal",
"expected": [
"clip03"
],
"id": "q032",
"intervals": {
"clip03": [
[
3.5,
5.05
]
]
},
"language": "de",
"negative_intervals": {
"clip03": [
[
0,
1.0
]
]
},
"text": "die rote Blume mit weit geöffneten Blütenblättern"
},
"query_ms": 93.10799999999999,
"segment_top5": [
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 79000
},
"start_s": 79.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 8.2,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6200
},
"start_s": 6.2
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-scene",
"expected": [
"clip02"
],
"hard_negatives": [
"image03",
"image05",
"image11"
],
"id": "q033",
"intervals": {
"clip02": [
[
0,
13.81
]
]
},
"language": "en",
"text": "the tall waterfall on a foggy rocky mountain"
},
"query_ms": 95.84049999999999,
"segment_top5": [
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 8.2,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6200
},
"start_s": 6.2
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-scene",
"expected": [
"clip02"
],
"hard_negatives": [
"image03",
"image05",
"image11"
],
"id": "q034",
"intervals": {
"clip02": [
[
0,
13.81
]
]
},
"language": "de",
"text": "der hohe Wasserfall an einem nebligen felsigen Berg"
},
"query_ms": 101.701,
"segment_top5": [
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4574
},
"start_s": 4.574
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-scene",
"expected": [
"clip04"
],
"id": "q035",
"intervals": {
"clip04": [
[
10,
20
]
]
},
"language": "en",
"text": "the astronaut standing on the Moon next to landing equipment"
},
"query_ms": 92.6443,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-scene",
"expected": [
"clip04"
],
"id": "q036",
"intervals": {
"clip04": [
[
10,
20
]
]
},
"language": "de",
"text": "der Astronaut auf dem Mond neben der Landeausrüstung"
},
"query_ms": 93.829,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 16.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 14000
},
"start_s": 14.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 26.167,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 24167
},
"start_s": 24.167
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-scene",
"expected": [
"clip04"
],
"id": "q037",
"intervals": {
"clip04": [
[
24,
33
]
]
},
"language": "en",
"text": "the lunar rover driving over grey Moon terrain"
},
"query_ms": 86.7595,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 26.167,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 24167
},
"start_s": 24.167
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 28.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 26000
},
"start_s": 26.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-scene",
"expected": [
"clip04"
],
"id": "q038",
"intervals": {
"clip04": [
[
24,
33
]
]
},
"language": "de",
"text": "der Mondrover fährt über graues Mondgelände"
},
"query_ms": 90.6467,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 28.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 26000
},
"start_s": 26.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q039",
"intervals": {
"clip04": [
[
1.551,
3.603
]
]
},
"language": "en",
"required_modality": "audio",
"text": "someone saying that we choose to go to the Moon"
},
"query_ms": 93.28609999999999,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q040",
"intervals": {
"clip04": [
[
1.551,
3.603
]
]
},
"language": "de",
"required_modality": "audio",
"text": "jemand sagt, dass wir uns entscheiden, zum Mond zu fliegen"
},
"query_ms": 101.9786,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 26.167,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 24167
},
"start_s": 24.167
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4574
},
"start_s": 4.574
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 8.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6000
},
"start_s": 6.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q041",
"intervals": {
"clip04": [
[
13.129,
16.316
]
]
},
"language": "en",
"required_modality": "audio",
"text": "someone finding orange soil on the Moon"
},
"query_ms": 77.0622,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 26.167,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 24167
},
"start_s": 24.167
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4574
},
"start_s": 4.574
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 8.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6000
},
"start_s": 6.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 14.467,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 12467
},
"start_s": 12.467
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4574
},
"start_s": 4.574
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 12.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 10000
},
"start_s": 10.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q042",
"intervals": {
"clip04": [
[
13.129,
16.316
]
]
},
"language": "de",
"required_modality": "audio",
"text": "jemand findet orangefarbenen Boden auf dem Mond"
},
"query_ms": 90.16929999999999,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 14.467,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 12467
},
"start_s": 12.467
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4574
},
"start_s": 4.574
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 12.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 10000
},
"start_s": 10.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 50.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 40000
},
"start_s": 40.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q043",
"intervals": {
"clip04": [
[
43.777,
52.419
]
]
},
"language": "en",
"required_modality": "audio",
"text": "a request to fund the Artemis program for the first woman on the Moon"
},
"query_ms": 110.4239,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 50.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 40000
},
"start_s": 40.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 58.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 48000
},
"start_s": 48.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q044",
"intervals": {
"clip04": [
[
43.777,
52.419
]
]
},
"language": "de",
"required_modality": "audio",
"text": "eine Bitte um Finanzierung von Artemis für die erste Frau auf dem Mond"
},
"query_ms": 104.9276,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 58.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 48000
},
"start_s": 48.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 66.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 56000
},
"start_s": 56.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q045",
"intervals": {
"clip04": [
[
56.539,
63.496
]
]
},
"language": "en",
"required_modality": "audio",
"text": "someone talking about planting a flag on Mars"
},
"query_ms": 82.19930000000001,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 66.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 56000
},
"start_s": 56.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 66.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 56000
},
"start_s": 56.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "video-speech",
"expected": [
"clip04"
],
"id": "q046",
"intervals": {
"clip04": [
[
56.539,
63.496
]
]
},
"language": "de",
"required_modality": "audio",
"text": "jemand spricht davon, eine Flagge auf dem Mars aufzustellen"
},
"query_ms": 97.2805,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 66.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 56000
},
"start_s": 56.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 90.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "music-memory",
"expected": [
"music01"
],
"hard_negatives": [
"music02"
],
"id": "q047",
"intervals": {
"music01": [
[
0,
254.45
]
]
},
"language": "en",
"required_modality": "audio",
"text": "gentle solo piano music without anyone singing"
},
"query_ms": 84.68,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 90.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 106.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 96000
},
"start_s": 96.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "music-memory",
"expected": [
"music01"
],
"hard_negatives": [
"music02"
],
"id": "q048",
"intervals": {
"music01": [
[
0,
254.45
]
]
},
"language": "de",
"required_modality": "audio",
"text": "sanfte Klaviermusik ohne Gesang"
},
"query_ms": 88.9702,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 106.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 96000
},
"start_s": 96.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 162.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 152000
},
"start_s": 152.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "music-memory",
"expected": [
"music02"
],
"hard_negatives": [
"music01"
],
"id": "q049",
"intervals": {
"music02": [
[
0,
30
]
]
},
"language": "en",
"required_modality": "audio",
"text": "a jazzy violin melody"
},
"query_ms": 78.158,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 162.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 152000
},
"start_s": 152.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 162.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 152000
},
"start_s": 152.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 72000
},
"start_s": 72.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "music-memory",
"expected": [
"music02"
],
"hard_negatives": [
"music01"
],
"id": "q050",
"intervals": {
"music02": [
[
0,
30
]
]
},
"language": "de",
"required_modality": "audio",
"text": "eine jazzige Geigenmelodie"
},
"query_ms": 91.0936,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 162.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 152000
},
"start_s": 152.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 72000
},
"start_s": 72.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "sound-memory",
"expected": [
"sound01"
],
"hard_negatives": [
"sound02"
],
"id": "q051",
"intervals": {
"sound01": [
[
0,
2.039
]
]
},
"language": "en",
"required_modality": "audio",
"text": "a dog barking nearby"
},
"query_ms": 65.364,
"segment_top5": [
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "sound-memory",
"expected": [
"sound01"
],
"hard_negatives": [
"sound02"
],
"id": "q052",
"intervals": {
"sound01": [
[
0,
2.039
]
]
},
"language": "de",
"required_modality": "audio",
"text": "ein Hund bellt in der Nähe"
},
"query_ms": 78.8284,
"segment_top5": [
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 80000
},
"start_s": 80.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip04",
"end_s": 52.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 50000
},
"start_s": 50.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "sound-memory",
"expected": [
"sound02"
],
"hard_negatives": [
"sound01"
],
"id": "q053",
"intervals": {
"sound02": [
[
0,
2.074
]
]
},
"language": "en",
"required_modality": "audio",
"text": "a growling roaring creature sound effect"
},
"query_ms": 77.5705,
"segment_top5": [
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip04",
"end_s": 80.63,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 72000
},
"start_s": 72.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "sound-memory",
"expected": [
"sound02"
],
"hard_negatives": [
"sound01"
],
"id": "q054",
"intervals": {
"sound02": [
[
0,
2.074
]
]
},
"language": "de",
"required_modality": "audio",
"text": "ein knurrender brüllender Kreatur-Soundeffekt"
},
"query_ms": 104.4495,
"segment_top5": [
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"match_kind": "media_metadata",
"modality": "metadata",
"source": null
},
"score": 0.031544957774465976
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18000
},
"start_s": 18.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip03",
"end_s": 4.005,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 2005
},
"start_s": 2.005
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "music02",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "exact-metadata",
"expected": [
"music01"
],
"id": "q055",
"language": "en",
"metadata": {
"artist": "Kimiko Ishizaka"
},
"text": "Kimiko Ishizaka"
},
"query_ms": 72.2521,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"match_kind": "media_metadata",
"modality": "metadata",
"source": null
},
"score": 0.031544957774465976
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18000
},
"start_s": 18.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music02",
"match_kind": "media_metadata",
"modality": "metadata",
"source": null
},
"score": 0.03252247488101534
},
{
"candidate": {
"asset": "music01",
"end_s": 58.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 48000
},
"start_s": 48.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "exact-metadata",
"expected": [
"music02"
],
"id": "q056",
"language": "en",
"metadata": {
"title": "Jazz Violin Solo"
},
"text": "Jazz Violin Solo"
},
"query_ms": 62.5772,
"segment_top5": [
{
"candidate": {
"asset": "music02",
"match_kind": "media_metadata",
"modality": "metadata",
"source": null
},
"score": 0.03252247488101534
},
{
"candidate": {
"asset": "music01",
"end_s": 58.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 48000
},
"start_s": 48.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music02",
"match_kind": "media_metadata",
"modality": "metadata",
"source": null
},
"score": 0.03278688524590164
},
{
"candidate": {
"asset": "music01",
"end_s": 34.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 8.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6000
},
"start_s": 6.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "exact-metadata",
"expected": [
"music02"
],
"id": "q057",
"language": "en",
"metadata": {
"artist": "Violinist WTD"
},
"text": "Violinist WTD"
},
"query_ms": 68.46090000000001,
"segment_top5": [
{
"candidate": {
"asset": "music02",
"match_kind": "media_metadata",
"modality": "metadata",
"source": null
},
"score": 0.03278688524590164
},
{
"candidate": {
"asset": "music01",
"end_s": 34.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 8.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6000
},
"start_s": 6.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
}
],
"query": {
"category": "exact-filter",
"expected": [
"image05"
],
"filters": {
"extension": "jpg"
},
"id": "q058",
"language": "en",
"text": "wooden pier under the moon"
},
"query_ms": 70.4285,
"segment_top5": [
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015384615384615385
}
]
},
{
"query": {
"category": "temporal-negative",
"expected": [],
"filters": {
"asset": "clip01",
"time_range_s": [
7,
14
]
},
"id": "q059",
"language": "en",
"required_modality": "image",
"text": "the cat jumping beside the handle"
},
"unsupported": "Production query API has no temporal-range filter yet"
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
}
],
"query": {
"category": "filter-no-answer",
"expected": [],
"filters": {
"extension": "ogg"
},
"id": "q060",
"language": "en",
"required_modality": "audio",
"text": "someone mentioning Mars"
},
"query_ms": 59.4506,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip01",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "content-no-answer",
"expected": [],
"id": "q061",
"language": "en",
"split": "held-out-no-answer",
"text": "a purple elephant playing a violin on the beach"
},
"query_ms": 84.11349999999999,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 31.233,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 29233
},
"start_s": 29.233
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4007
},
"start_s": 4.007
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip01",
"end_s": 18.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip02",
"end_s": 10.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "content-no-answer",
"expected": [],
"id": "q062",
"language": "de",
"split": "held-out-no-answer",
"text": "ein violetter Elefant spielt Geige am Strand"
},
"query_ms": 92.2089,
"segment_top5": [
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip04",
"end_s": 20.3,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 18300
},
"start_s": 18.3
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "speech-no-answer",
"expected": [],
"id": "q063",
"language": "en",
"required_modality": "audio",
"split": "held-out-no-answer",
"text": "someone explains quantum entanglement"
},
"query_ms": 67.82000000000001,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 26.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 16000
},
"start_s": 16.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.015625
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 8.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6000
},
"start_s": 6.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "clip02",
"end_s": 13.81,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 8000
},
"start_s": 8.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "speech-no-answer",
"expected": [],
"id": "q064",
"language": "de",
"required_modality": "audio",
"split": "held-out-no-answer",
"text": "jemand erklärt Quantenverschränkung"
},
"query_ms": 76.2701,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 8.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 6000
},
"start_s": 6.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "clip01",
"end_s": 22.204,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 21733
},
"start_s": 21.733
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
},
{
"file_rankings": [
{
"candidate": {
"asset": "clip04",
"end_s": 74.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 72000
},
"start_s": 72.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
},
{
"candidate": {
"asset": "clip01",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.015151515151515152
},
{
"candidate": {
"asset": "music02",
"end_s": 30.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 24000
},
"start_s": 24.0
},
"score": 0.014925373134328358
},
{
"candidate": {
"asset": "image12",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014705882352941176
},
{
"candidate": {
"asset": "clip02",
"end_s": 6.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 4000
},
"start_s": 4.0
},
"score": 0.014492753623188406
},
{
"candidate": {
"asset": "image11",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014285714285714285
},
{
"candidate": {
"asset": "image05",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.014084507042253521
},
{
"candidate": {
"asset": "image06",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013888888888888888
},
{
"candidate": {
"asset": "image01",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0136986301369863
},
{
"candidate": {
"asset": "image10",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013513513513513514
},
{
"candidate": {
"asset": "image02",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013333333333333334
},
{
"candidate": {
"asset": "image04",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.013157894736842105
},
{
"candidate": {
"asset": "image03",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012987012987012988
},
{
"candidate": {
"asset": "image08",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.01282051282051282
},
{
"candidate": {
"asset": "image09",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.012658227848101266
},
{
"candidate": {
"asset": "image07",
"match_kind": "semantic_image",
"modality": "image",
"source": {
"kind": "image",
"number": 0
}
},
"score": 0.0125
}
],
"query": {
"category": "metadata-no-answer",
"expected": [],
"id": "q065",
"language": "en",
"metadata": {
"artist": "Adele"
},
"text": "Adele"
},
"query_ms": 52.9589,
"segment_top5": [
{
"candidate": {
"asset": "clip04",
"end_s": 74.0,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_video",
"modality": "image",
"source": {
"kind": "timestamp_ms",
"number": 72000
},
"start_s": 72.0
},
"score": 0.01639344262295082
},
{
"candidate": {
"asset": "music01",
"end_s": 254.453333,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 248000
},
"start_s": 248.0
},
"score": 0.016129032258064516
},
{
"candidate": {
"asset": "clip03",
"end_s": 5.056,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015873015873015872
},
{
"candidate": {
"asset": "sound02",
"end_s": 2.074218,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015625
},
{
"candidate": {
"asset": "sound01",
"end_s": 2.038594,
"interval_note": "End inferred from configured pipeline window policy, actual API exposes only start timestamp",
"match_kind": "semantic_audio",
"modality": "audio",
"source": {
"kind": "timestamp_ms",
"number": 0
},
"start_s": 0.0
},
"score": 0.015384615384615385
}
]
}
],
"scope": "Actual Searchi hybrid pipeline and native extension filters; temporal-range filter unsupported; segment ends inferred from configured audio/frame policy, exact point timestamps come from actual result API",
"worker": {
"device": "cpu",
"dimensions": 768,
"media_supported": true,
"model": "google/embeddinggemma-2",
"ready": true,
"runtime": "b11461-no-logits-v1",
"threads": 1
}
}
Reference in new issue View Git Blame Copy Permalink