Files
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

1362 lines
37 KiB
JSON

{
"version": 1,
"label_policy": "Labels independently authored from actual images/frames and publisher speech timestamps BEFORE media model inference. Never adjust v1 labels after inspecting rankings. Create a new version for corrections. No hand-tuned rejection threshold.",
"created_utc": "2026-10-12T15:59:36.850393+00:00",
"assets": [
{
"id": "image01",
"path": "assets/image01.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/126407/pexels-photo-126407.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/126407/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Long-haired tabby cat lying flat indoors, eyes toward camera.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 27390,
"sha256": "c0b2ebddafcff4cd60ae1d2f1b8e53d4e0f11643ac53d0113605f333523b21ed"
},
{
"id": "image02",
"path": "assets/image02.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/1099680/pexels-photo-1099680.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/1099680/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Fruit bowl with raspberries, mango, blackberries, strawberries and almonds, top down.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 68905,
"sha256": "72b46006e7f55dcad5bec5af977171a369917030cf2ff99e544806af939ffec1"
},
{
"id": "image03",
"path": "assets/image03.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/459225/pexels-photo-459225.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/459225/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Jagged mountains and fir trees reflected in a daylight lake.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 34309,
"sha256": "c4abbb061e6fcbcef25d36d7bb7f24018c0c768b23176fb2a77a9eb8f5b86f21"
},
{
"id": "image04",
"path": "assets/image04.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/355465/pexels-photo-355465.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/355465/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Dense blue star field and Milky Way above a dark mountain landscape.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 37735,
"sha256": "8999f22131c22ee1c29d79dda352c2654131eb1b4f61ba7f8b8d21dbbc5cc791"
},
{
"id": "image05",
"path": "assets/image05.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/414612/pexels-photo-414612.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/414612/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Wooden pier into still lake at night under a bright moon.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 51106,
"sha256": "1cfd9d9c3dea4ec4e1733c55424eef93983bce1167f60777768cae6c549fd889"
},
{
"id": "image06",
"path": "assets/image06.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/1323550/pexels-photo-1323550.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/1323550/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Layered purple mountains under a yellow-orange sunset, tiny person on ridge.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 27259,
"sha256": "91947e87067c923db2e560f67cdd0c1edec55c9bb0fbab6a83ee7c7adf88860d"
},
{
"id": "image07",
"path": "assets/image07.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/841303/pexels-photo-841303.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/841303/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Cows grazing in green rolling hills.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 50633,
"sha256": "0b0cc8c211680d19ebdaf2b797af430120c4e65f951143bbe06544eaa0691942"
},
{
"id": "image08",
"path": "assets/image08.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/210019/pexels-photo-210019.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/210019/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Red sports coupe on a wooded road, motion-blurred background.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 65362,
"sha256": "12b5fd662c054d1337e4adf733751da3e32c1fd40f88dfccc0bd73af4f620369"
},
{
"id": "image09",
"path": "assets/image09.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/1640777/pexels-photo-1640777.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/1640777/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Bowl of quinoa and vegetables, sliced carrots and zucchini on pale table.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 68469,
"sha256": "6112af5f9ed170d91c7f8e1e5de95142c0190e2e2f8fbbbccf2f106553371817"
},
{
"id": "image10",
"path": "assets/image10.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/302899/pexels-photo-302899.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/302899/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Milk pouring from metal jug into cup of coffee with latte art.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 23609,
"sha256": "632926d3bd0f4691ae7fd0a8e2cb8b455e0252511eebf322e91c64c17cdf0e2a"
},
{
"id": "image11",
"path": "assets/image11.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/248797/pexels-photo-248797.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/248797/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Turquoise tropical sea and white beach fringed by green vegetation.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 27716,
"sha256": "c02ad4a8bbe8091cbc3a9a0abc602a905cb46056efa94141950f3af1c749c038"
},
{
"id": "image12",
"path": "assets/image12.jpg",
"kind": "image",
"source_url": "https://images.pexels.com/photos/167964/pexels-photo-167964.jpeg?auto=compress&cs=tinysrgb&w=640",
"source_page": "https://www.pexels.com/photo/167964/",
"license": "Pexels License",
"license_url": "https://www.pexels.com/license/",
"changes": "Publisher-provided 640px compressed derivative, no local pixel changes.",
"observation": "Black and white silhouette of a person reaching a hand toward camera.",
"independent_inspection": "view_image before any media embedding inference",
"bytes": 14256,
"sha256": "dd3bc409128a8702522bac7b953a5eb691662eebf21ac3ba0b3b15c70f86d54b"
},
{
"id": "clip01",
"path": "assets/clip01.webm",
"kind": "video",
"duration_s": 22.204,
"source_url": "https://upload.wikimedia.org/wikipedia/commons/c/cc/Cat_opening_door.webm",
"source_page": "https://commons.wikimedia.org/wiki/File:Cat_opening_door.webm",
"license": "CC-BY-SA-4.0",
"license_url": "https://creativecommons.org/licenses/by-sa/4.0/",
"author": "Astropulse",
"changes": "None; downloaded original file.",
"observation": "Orange tabby cat twice jumps against white door near its lever, then crouches.",
"independent_inspection": "Real frames viewed before inference; NASA speech labels use publisher SRT, never model outputs.",
"bytes": 2253125,
"sha256": "1a1f420559b306574ba8a04aee0175c38c2e20815b1bd46a45aae86d17f3ad53"
},
{
"id": "clip02",
"path": "assets/clip02.webm",
"kind": "video",
"duration_s": 13.81,
"source_url": "https://upload.wikimedia.org/wikipedia/commons/c/c9/Water_flowing_strem.webm",
"source_page": "https://commons.wikimedia.org/wiki/File:Water_flowing_strem.webm",
"license": "CC0-1.0",
"license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
"author": "BhotaRohit",
"changes": "None; downloaded original file.",
"observation": "Tall waterfall descending misty rocky hillside; a tiny person appears near its base.",
"independent_inspection": "Real frames viewed before inference; NASA speech labels use publisher SRT, never model outputs.",
"bytes": 6001205,
"sha256": "5652e6490bea85dfb7a1da05e00fc7f3d8cc2cbd54790c03a48223f2256bc3d1"
},
{
"id": "clip03",
"path": "assets/clip03.webm",
"kind": "video",
"duration_s": 5.056,
"source_url": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.webm",
"source_page": "https://github.com/mdn/interactive-examples",
"license": "CC0-1.0",
"license_url": "https://raw.githubusercontent.com/mdn/interactive-examples/main/LICENSE",
"author": "MDN contributors",
"changes": "None; downloaded original file.",
"observation": "Timelapse of closed red flower bud opening among green purple-edged leaves.",
"independent_inspection": "Real frames viewed before inference; NASA speech labels use publisher SRT, never model outputs.",
"bytes": 554058,
"sha256": "c6f8a348953395598a9a73b9bab1676436410797bce9f398f4be1531d6e76dda"
},
{
"id": "clip04",
"path": "assets/clip04.mp4",
"kind": "video",
"duration_s": 80.63,
"source_url": "https://images-assets.nasa.gov/video/Artemis%20Origins/Artemis%20Origins~small.mp4",
"source_page": "https://images.nasa.gov/details/Artemis%20Origins",
"license": "NASA informational media permission",
"license_url": "https://www.nasa.gov/nasa-brand-center/images-and-media/",
"author": "NASA",
"changes": "None; downloaded original file.",
"observation": "Artemis Origins montage: Apollo astronauts, lunar surface/rover, a speech and future-space imagery. Speech intervals independently labelled from NASA publisher SRT.",
"independent_inspection": "Real frames viewed before inference; NASA speech labels use publisher SRT, never model outputs.",
"bytes": 16710310,
"sha256": "5fa4af30f984f4d7d53b50990d1e21e41df50b62a8b3ec3a2a1d44f30431f0f1"
},
{
"id": "music01",
"path": "assets/music01.ogg",
"kind": "music",
"source_url": "https://upload.wikimedia.org/wikipedia/commons/4/49/Kimiko_Ishizaka_-_14_-_Variatio_13_a_2_Clav.ogg",
"source_page": "https://commons.wikimedia.org/wiki/File:Kimiko_Ishizaka_-_14_-_Variatio_13_a_2_Clav.ogg",
"license": "CC0-1.0",
"license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
"author": "Kimiko Ishizaka",
"changes": "None; original waveform and embedded metadata retained.",
"observation": "Soft solo piano performance of Bach Goldberg Variation13, original Vorbis artist/title tags retained.",
"duration_s": 254.453333,
"tags": {
"encoder": "Lavc58.54.100 libvorbis",
"title": "Variatio 13 a 2 Clav.",
"artist": "Kimiko Ishizaka",
"track": "14",
"album": "The Open Goldberg Variations",
"disc": "1",
"date": "2012-05-29T17:49:26",
"genre": "Classical",
"copyright": "CC0 1.0 Universal: http://creativecommons.org/publicdomain/zero/1.0/",
"tdat": "2012-05-29 17:49:26",
"comment": "URL: http://freemusicarchive.org/music/Kimiko_Ishizaka/The_Open_Goldberg_Variations/KIMIKO_ISHIZAKA_-_Goldberg_Variations_BWV_988_-_14_-_Variatio_13_a_2_Clav__44k-24b\r\nComments: http://freemusicarchive.org/\r\nCurator: ccCommunity\r\nCopyright: CC0 1.0 Universal: http://creativecommons.org/publicdomain/zero/1.0/\r\nComposer: J.S. Bach",
"tlen": "254453",
"tsrc": "QMNYZ1200014",
"composer": "J.S. Bach",
"album_artist": "Kimiko Ishizaka"
},
"independent_inspection": "Publisher descriptions and original FFprobe tags checked before inference. Audio perception not claimed as human listening.",
"bytes": 4697594,
"sha256": "29fcd20414ee19c2a5aa4339eaf6375079dc87959051ab0aea32c76df52f34dc"
},
{
"id": "music02",
"path": "assets/music02.ogg",
"kind": "music",
"source_url": "https://upload.wikimedia.org/wikipedia/commons/3/37/00_Jazz_Violin_Solo.ogg",
"source_page": "https://commons.wikimedia.org/wiki/File:00_Jazz_Violin_Solo.ogg",
"license": "PD-self",
"license_url": "https://commons.wikimedia.org/wiki/File:00_Jazz_Violin_Solo.ogg",
"author": "VWD",
"changes": "None; original waveform and embedded metadata retained.",
"observation": "Jazz violin solo, original Vorbis tags identify artist Violinist WTD and title Jazz Violin Solo.",
"duration_s": 30.0,
"tags": {
"album": "2007 Spring Concert Series",
"artist": "Violinist WTD",
"composer": "Violinist WTD/LPC Jazz Band",
"date": "2007",
"encoder": "Max 0.7.1",
"encoding": "Vorbis settings: VBR(q=3.000000)",
"genre": "Jazz",
"title": "Jazz Violin Solo"
},
"independent_inspection": "Publisher descriptions and original FFprobe tags checked before inference. Audio perception not claimed as human listening.",
"bytes": 198070,
"sha256": "9ce9c5d07f941c07cab575e58016d6ad1b09219a36477652118d8e85c3401dd8"
},
{
"id": "sound01",
"path": "assets/sound01.wav",
"kind": "sound",
"source_url": "https://opengameart.org/sites/default/files/dog_barking_mono.wav",
"source_page": "https://opengameart.org/content/dog-barking-mono",
"license": "CC0-1.0",
"license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
"author": "Brandon Morris (uploaded by HaelDB)",
"changes": "None; original waveform and embedded metadata retained.",
"observation": "Dog bark recording from independently described source; real waveform retained.",
"duration_s": 2.038594,
"tags": {},
"independent_inspection": "Publisher descriptions and original FFprobe tags checked before inference. Audio perception not claimed as human listening.",
"bytes": 179848,
"sha256": "bbd0f908b3514dd3bd7d2bc04dcf64f8d360a161e7f43cac5d6761e7add79451"
},
{
"id": "sound02",
"path": "assets/sound02.mp3",
"kind": "sound",
"source_url": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
"source_page": "https://github.com/mdn/interactive-examples",
"license": "CC0-1.0",
"license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
"author": "MDN contributors",
"changes": "None; original waveform and embedded metadata retained.",
"observation": "Roaring creature sound effect from independently described CC0 source; real waveform retained.",
"duration_s": 2.074218,
"tags": {
"encoder": "LAME3.98r"
},
"independent_inspection": "Publisher descriptions and original FFprobe tags checked before inference. Audio perception not claimed as human listening.",
"bytes": 39868,
"sha256": "41191d0727073bf848bcc8f0bd851d71a0b0058e901abb1c1b236ad327bda52e"
}
],
"queries": [
{
"id": "q001",
"text": "the fluffy striped cat resting with its chin on the floor",
"language": "en",
"expected": [
"image01"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q002",
"text": "die flauschige gestreifte Katze liegt mit dem Kinn auf dem Boden",
"language": "de",
"expected": [
"image01"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q003",
"text": "the overhead breakfast bowl with berries and diced mango",
"language": "en",
"expected": [
"image02"
],
"category": "image-memory",
"hard_negatives": [
"image09"
]
},
{
"id": "q004",
"text": "die Frühstücksschüssel mit Beeren und gewürfelter Mango von oben",
"language": "de",
"expected": [
"image02"
],
"category": "image-memory",
"hard_negatives": [
"image09"
]
},
{
"id": "q005",
"text": "the daytime lake reflecting jagged mountains and pine trees",
"language": "en",
"expected": [
"image03"
],
"category": "image-memory",
"hard_negatives": [
"image05",
"image06",
"image04"
]
},
{
"id": "q006",
"text": "der See bei Tageslicht spiegelt schroffe Berge und Tannen",
"language": "de",
"expected": [
"image03"
],
"category": "image-memory",
"hard_negatives": [
"image05",
"image06",
"image04"
]
},
{
"id": "q007",
"text": "the Milky Way over a dark mountain valley",
"language": "en",
"expected": [
"image04"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q008",
"text": "die Milchstraße über einem dunklen Bergtal",
"language": "de",
"expected": [
"image04"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q009",
"text": "the wooden jetty pointing into a lake under moonlight",
"language": "en",
"expected": [
"image05"
],
"category": "image-memory",
"hard_negatives": [
"image03",
"image04"
]
},
{
"id": "q010",
"text": "der Holzsteg führt bei Mondlicht in einen See",
"language": "de",
"expected": [
"image05"
],
"category": "image-memory",
"hard_negatives": [
"image03",
"image04"
]
},
{
"id": "q011",
"text": "the pink layered mountain ridges beneath a golden sunset",
"language": "en",
"expected": [
"image06"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q012",
"text": "die rosa Bergketten unter einem goldenen Sonnenuntergang",
"language": "de",
"expected": [
"image06"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q013",
"text": "the herd of cows on green hills",
"language": "en",
"expected": [
"image07"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q014",
"text": "die Kuhherde auf grünen Hügeln",
"language": "de",
"expected": [
"image07"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q015",
"text": "the red sports car driving through woods",
"language": "en",
"expected": [
"image08"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q016",
"text": "das rote Sportauto fährt durch den Wald",
"language": "de",
"expected": [
"image08"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q017",
"text": "the vegetable and grain bowl beside carrot slices",
"language": "en",
"expected": [
"image09"
],
"category": "image-memory",
"hard_negatives": [
"image02"
]
},
{
"id": "q018",
"text": "die Gemüse-Getreide-Schüssel neben Karottenscheiben",
"language": "de",
"expected": [
"image09"
],
"category": "image-memory",
"hard_negatives": [
"image02"
]
},
{
"id": "q019",
"text": "milk being poured into coffee to make a pattern",
"language": "en",
"expected": [
"image10"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q020",
"text": "Milch wird für ein Muster in den Kaffee gegossen",
"language": "de",
"expected": [
"image10"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q021",
"text": "the empty tropical beach with turquoise water",
"language": "en",
"expected": [
"image11"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q022",
"text": "der leere tropische Strand mit türkisfarbenem Wasser",
"language": "de",
"expected": [
"image11"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q023",
"text": "the black and white photo with a hand reaching towards us",
"language": "en",
"expected": [
"image12"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q024",
"text": "das Schwarzweißfoto mit einer Hand, die nach uns greift",
"language": "de",
"expected": [
"image12"
],
"category": "image-memory",
"hard_negatives": []
},
{
"id": "q025",
"text": "the cat jumping up beside a door handle",
"language": "en",
"expected": [
"clip01"
],
"category": "video-action",
"intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
},
"hard_negatives": [
"image01"
],
"negative_intervals": {
"clip01": [
[
7,
14
]
]
}
},
{
"id": "q026",
"text": "die Katze springt neben dem Türgriff hoch",
"language": "de",
"expected": [
"clip01"
],
"category": "video-action",
"intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
},
"hard_negatives": [
"image01"
],
"negative_intervals": {
"clip01": [
[
7,
14
]
]
}
},
{
"id": "q027",
"text": "the cat sitting low by the door after trying to open it",
"language": "en",
"expected": [
"clip01"
],
"category": "video-action",
"intervals": {
"clip01": [
[
7,
14
]
]
},
"negative_intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
}
},
{
"id": "q028",
"text": "die Katze sitzt nach dem Öffnungsversuch unten an der Tür",
"language": "de",
"expected": [
"clip01"
],
"category": "video-action",
"intervals": {
"clip01": [
[
7,
14
]
]
},
"negative_intervals": {
"clip01": [
[
2,
4.9
],
[
15.5,
17.5
]
]
}
},
{
"id": "q029",
"text": "the red flower bud before its petals open",
"language": "en",
"expected": [
"clip03"
],
"category": "video-temporal",
"intervals": {
"clip03": [
[
0,
1.0
]
]
},
"negative_intervals": {
"clip03": [
[
3.5,
5.05
]
]
}
},
{
"id": "q030",
"text": "die rote Blütenknospe bevor sich die Blätter öffnen",
"language": "de",
"expected": [
"clip03"
],
"category": "video-temporal",
"intervals": {
"clip03": [
[
0,
1.0
]
]
},
"negative_intervals": {
"clip03": [
[
3.5,
5.05
]
]
}
},
{
"id": "q031",
"text": "the red flower with its petals open wide",
"language": "en",
"expected": [
"clip03"
],
"category": "video-temporal",
"intervals": {
"clip03": [
[
3.5,
5.05
]
]
},
"negative_intervals": {
"clip03": [
[
0,
1.0
]
]
}
},
{
"id": "q032",
"text": "die rote Blume mit weit geöffneten Blütenblättern",
"language": "de",
"expected": [
"clip03"
],
"category": "video-temporal",
"intervals": {
"clip03": [
[
3.5,
5.05
]
]
},
"negative_intervals": {
"clip03": [
[
0,
1.0
]
]
}
},
{
"id": "q033",
"text": "the tall waterfall on a foggy rocky mountain",
"language": "en",
"expected": [
"clip02"
],
"category": "video-scene",
"intervals": {
"clip02": [
[
0,
13.81
]
]
},
"hard_negatives": [
"image03",
"image05",
"image11"
]
},
{
"id": "q034",
"text": "der hohe Wasserfall an einem nebligen felsigen Berg",
"language": "de",
"expected": [
"clip02"
],
"category": "video-scene",
"intervals": {
"clip02": [
[
0,
13.81
]
]
},
"hard_negatives": [
"image03",
"image05",
"image11"
]
},
{
"id": "q035",
"text": "the astronaut standing on the Moon next to landing equipment",
"language": "en",
"expected": [
"clip04"
],
"category": "video-scene",
"intervals": {
"clip04": [
[
10,
20
]
]
}
},
{
"id": "q036",
"text": "der Astronaut auf dem Mond neben der Landeausrüstung",
"language": "de",
"expected": [
"clip04"
],
"category": "video-scene",
"intervals": {
"clip04": [
[
10,
20
]
]
}
},
{
"id": "q037",
"text": "the lunar rover driving over grey Moon terrain",
"language": "en",
"expected": [
"clip04"
],
"category": "video-scene",
"intervals": {
"clip04": [
[
24,
33
]
]
}
},
{
"id": "q038",
"text": "der Mondrover fährt über graues Mondgelände",
"language": "de",
"expected": [
"clip04"
],
"category": "video-scene",
"intervals": {
"clip04": [
[
24,
33
]
]
}
},
{
"id": "q039",
"text": "someone saying that we choose to go to the Moon",
"language": "en",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
1.551,
3.603
]
]
},
"required_modality": "audio"
},
{
"id": "q040",
"text": "jemand sagt, dass wir uns entscheiden, zum Mond zu fliegen",
"language": "de",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
1.551,
3.603
]
]
},
"required_modality": "audio"
},
{
"id": "q041",
"text": "someone finding orange soil on the Moon",
"language": "en",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
13.129,
16.316
]
]
},
"required_modality": "audio"
},
{
"id": "q042",
"text": "jemand findet orangefarbenen Boden auf dem Mond",
"language": "de",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
13.129,
16.316
]
]
},
"required_modality": "audio"
},
{
"id": "q043",
"text": "a request to fund the Artemis program for the first woman on the Moon",
"language": "en",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
43.777,
52.419
]
]
},
"required_modality": "audio"
},
{
"id": "q044",
"text": "eine Bitte um Finanzierung von Artemis für die erste Frau auf dem Mond",
"language": "de",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
43.777,
52.419
]
]
},
"required_modality": "audio"
},
{
"id": "q045",
"text": "someone talking about planting a flag on Mars",
"language": "en",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
56.539,
63.496
]
]
},
"required_modality": "audio"
},
{
"id": "q046",
"text": "jemand spricht davon, eine Flagge auf dem Mars aufzustellen",
"language": "de",
"expected": [
"clip04"
],
"category": "video-speech",
"intervals": {
"clip04": [
[
56.539,
63.496
]
]
},
"required_modality": "audio"
},
{
"id": "q047",
"text": "gentle solo piano music without anyone singing",
"language": "en",
"expected": [
"music01"
],
"category": "music-memory",
"intervals": {
"music01": [
[
0,
254.45
]
]
},
"required_modality": "audio",
"hard_negatives": [
"music02"
]
},
{
"id": "q048",
"text": "sanfte Klaviermusik ohne Gesang",
"language": "de",
"expected": [
"music01"
],
"category": "music-memory",
"intervals": {
"music01": [
[
0,
254.45
]
]
},
"required_modality": "audio",
"hard_negatives": [
"music02"
]
},
{
"id": "q049",
"text": "a jazzy violin melody",
"language": "en",
"expected": [
"music02"
],
"category": "music-memory",
"intervals": {
"music02": [
[
0,
30
]
]
},
"required_modality": "audio",
"hard_negatives": [
"music01"
]
},
{
"id": "q050",
"text": "eine jazzige Geigenmelodie",
"language": "de",
"expected": [
"music02"
],
"category": "music-memory",
"intervals": {
"music02": [
[
0,
30
]
]
},
"required_modality": "audio",
"hard_negatives": [
"music01"
]
},
{
"id": "q051",
"text": "a dog barking nearby",
"language": "en",
"expected": [
"sound01"
],
"category": "sound-memory",
"intervals": {
"sound01": [
[
0,
2.039
]
]
},
"required_modality": "audio",
"hard_negatives": [
"sound02"
]
},
{
"id": "q052",
"text": "ein Hund bellt in der Nähe",
"language": "de",
"expected": [
"sound01"
],
"category": "sound-memory",
"intervals": {
"sound01": [
[
0,
2.039
]
]
},
"required_modality": "audio",
"hard_negatives": [
"sound02"
]
},
{
"id": "q053",
"text": "a growling roaring creature sound effect",
"language": "en",
"expected": [
"sound02"
],
"category": "sound-memory",
"intervals": {
"sound02": [
[
0,
2.074
]
]
},
"required_modality": "audio",
"hard_negatives": [
"sound01"
]
},
{
"id": "q054",
"text": "ein knurrender brüllender Kreatur-Soundeffekt",
"language": "de",
"expected": [
"sound02"
],
"category": "sound-memory",
"intervals": {
"sound02": [
[
0,
2.074
]
]
},
"required_modality": "audio",
"hard_negatives": [
"sound01"
]
},
{
"id": "q055",
"text": "Kimiko Ishizaka",
"language": "en",
"expected": [
"music01"
],
"category": "exact-metadata",
"metadata": {
"artist": "Kimiko Ishizaka"
}
},
{
"id": "q056",
"text": "Jazz Violin Solo",
"language": "en",
"expected": [
"music02"
],
"category": "exact-metadata",
"metadata": {
"title": "Jazz Violin Solo"
}
},
{
"id": "q057",
"text": "Violinist WTD",
"language": "en",
"expected": [
"music02"
],
"category": "exact-metadata",
"metadata": {
"artist": "Violinist WTD"
}
},
{
"id": "q058",
"text": "wooden pier under the moon",
"language": "en",
"expected": [
"image05"
],
"category": "exact-filter",
"filters": {
"extension": "jpg"
}
},
{
"id": "q059",
"text": "the cat jumping beside the handle",
"language": "en",
"expected": [],
"category": "temporal-negative",
"filters": {
"asset": "clip01",
"time_range_s": [
7,
14
]
},
"required_modality": "image"
},
{
"id": "q060",
"text": "someone mentioning Mars",
"language": "en",
"expected": [],
"category": "filter-no-answer",
"filters": {
"extension": "ogg"
},
"required_modality": "audio"
},
{
"id": "q061",
"text": "a purple elephant playing a violin on the beach",
"language": "en",
"expected": [],
"category": "content-no-answer",
"split": "held-out-no-answer"
},
{
"id": "q062",
"text": "ein violetter Elefant spielt Geige am Strand",
"language": "de",
"expected": [],
"category": "content-no-answer",
"split": "held-out-no-answer"
},
{
"id": "q063",
"text": "someone explains quantum entanglement",
"language": "en",
"expected": [],
"category": "speech-no-answer",
"required_modality": "audio",
"split": "held-out-no-answer"
},
{
"id": "q064",
"text": "jemand erklärt Quantenverschränkung",
"language": "de",
"expected": [],
"category": "speech-no-answer",
"required_modality": "audio",
"split": "held-out-no-answer"
},
{
"id": "q065",
"text": "Adele",
"language": "en",
"expected": [],
"category": "metadata-no-answer",
"metadata": {
"artist": "Adele"
}
}
]
}