diff --git a/apps/desktop/src-tauri/installer-hooks.nsh b/apps/desktop/src-tauri/installer-hooks.nsh
new file mode 100644
index 0000000..f1e23bb
--- /dev/null
+++ b/apps/desktop/src-tauri/installer-hooks.nsh
@@ -0,0 +1,4 @@
+; Keep duplicate native backends/redistributables compressible across the full
+; resource tree. This affects installer compression only, not application memory.
+; NSIS extraction needs approximately 128 MiB for this LZMA dictionary.
+SetCompressorDictSize 128
diff --git a/apps/desktop/src-tauri/tauri.conf.json b/apps/desktop/src-tauri/tauri.conf.json
index 5fe70cc..12ea296 100644
--- a/apps/desktop/src-tauri/tauri.conf.json
+++ b/apps/desktop/src-tauri/tauri.conf.json
@@ -26,6 +26,7 @@
   },
   "bundle": {
     "active": false,
+    "windows": { "nsis": { "installerHooks": "installer-hooks.nsh" } },
     "resources": { "resources/": "" },
     "icon": [
       "icons/32x32.png",
diff --git a/docs/SPEECH-INTEGRATION.md b/docs/SPEECH-INTEGRATION.md
index 288f35f..1ee794d 100644
--- a/docs/SPEECH-INTEGRATION.md
+++ b/docs/SPEECH-INTEGRATION.md
@@ -53,7 +53,7 @@ inference budget.
 
 - [x] Current CPU native worker English/German context reuse and Unicode paths.
 - [x] Actual shared-service ASR plus Google lifecycle integration.
-- [ ] Frozen independent four-file/ten-query and separate seam evaluation.
+- [x] Frozen independent four-file/ten-query and separate seam evaluation.
 - [ ] Normal hardware-detecting runtime staging and Windows package startup.
 - [ ] Publish/install the verified Windows update.
 - [ ] Native playback and graphical interaction, actual GPU execution, and
@@ -90,3 +90,35 @@ nested MSBuild path length. Its log is retained, SHA
 `59f1820d6ac6adac6f525d8084c442c1ed261753eb34fcce916dc157041f777c`.
 An unchanged build in a shorter owned output directory is underway; no CPU-only
 distribution was substituted.
+
+The shorter-path normal auto build subsequently completed. Worker SHA
+`0b716fa17e8216ed46c7755d15acab20f658254b99780c7a68bab03d765c55bc`,
+inventory SHA
+`0e116c604141af147bd91736ec0722a0660dcda8c9da008e494c464753f4e5a1`.
+It contains private Vulkan/CPU backends, loader and matching Microsoft runtime
+files. The current normal artifact passed genuine repeated English recognition
+from Unicode paths with CPU forced. Fifty owned-process samples observed the
+CPU backend and no Vulkan modules; sampling alone does not prove absence at
+every instant. The pinned CPU-only loading branch complements that observation.
+See [runtime evidence](../tools/speech-runtime/README.md).
+
+## Frozen independent retrieval
+
+The four-file fixture retained both real English/German recordings, instrumental
+music and silence, plus all ten frozen queries. Six positive queries found a
+relevant file first, with recall@5 also 6/6. Music and silence produced zero
+accepted recognized passages. **All four absent queries still returned files.**
+The two readings share translated subject matter; this is a small file-retrieval
+test, not broad media accuracy or verified passage/word timing.
+
+Every expected window input and published citation passed source validation,
+including four windows across the two separate artificial seam sources.
+Transcription errors, partial boundary phrases and overlap duplicates remain in
+the evidence. Concept substring coverage is not a word-error score. Root
+independently recomputed the exact recorded scorer output.
+
+The complete report is 174868 bytes, SHA
+`79ecb75d31c0193642c81862fd5476ad47adca518d4959e436bdd472cc281798`.
+It uses the internal v3 CPU artifact and does not establish normal auto runtime
+quality parity or GPU performance. Details and the retained comparison are in
+[the evaluator](../tools/speech-eval/native-validation/README.md).
diff --git a/tools/speech-runtime/README.md b/tools/speech-runtime/README.md
index 7ca788e..64dcdae 100644
--- a/tools/speech-runtime/README.md
+++ b/tools/speech-runtime/README.md
@@ -36,6 +36,27 @@ inventory SHA-256 `4904995685a5e55e0a790d9cc409dc8458e39c30cda4097c5d70bf75cb5c9
 This static CPU artifact does not prove normal dynamic-loader isolation, GPU
 execution, speech retrieval quality or precise independently annotated timing.
 
+The subsequent **normal Windows auto** build completed with all 27 inventoried
+files (58,913,466 bytes). Its worker SHA-256 is
+`0b716fa17e8216ed46c7755d15acab20f658254b99780c7a68bab03d765c55bc`;
+inventory SHA-256 `0e116c604141af147bd91736ec0722a0660dcda8c9da008e494c464753f4e5a1`.
+The same English Unicode/context test passed with forced CPU: first/warm ASR
+41.31/38.46 seconds, warm load zero, fallback zero. Packaging compilation overlapped
+this shared VM run, so these are functional timings, not a clean benchmark.
+Fifty snapshots of the owned worker observed `ggml-cpu-cascadelake.dll`,
+`ggml.dll`, `ggml-base.dll` and `whisper.dll`; neither `ggml-vulkan.dll` nor
+`vulkan-1.dll` was observed. The pinned CPU-only loader branch loads only the CPU
+module. Sampling alone does not prove that a module was never loaded.
+Ignored observation artifact SHA-256:
+`5a090b34e6a0d1ad88893295bc8db54e01f818db2ec20aca3c097d277720e158`.
+Actual GPU execution/fallback and other operating systems remain unexecuted.
+
+Windows MSBuild's nested Vulkan shader compiler failed with a long build output
+path; the failed log SHA-256 is
+`59f1820d6ac6adac6f525d8084c442c1ed261753eb34fcce916dc157041f777c`.
+An unchanged-source build using a shorter owned output path completed. Prefer a
+short build output directory on Windows; no CPU-only distribution was substituted.
+
 The persistent worker receives binary requests: operation byte (1 live VAD,
 2 contiguous recognition), little-endian u32 sample count and mono little-endian
 f32 PCM, at most 480000 finite samples. Responses have a four-byte little-endian