Document three encoder teacher cosine metrics

README.md

@@ -69,6 +69,18 @@ Download these from [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/Mini
 
 The showcase used one matched 1344x768, 243-frame, 24 FPS, 25-step T2V contract. The three source outputs and merged comparison are technical assets. They do not establish a visual-quality winner. The recovered 8B showcase uses the BF16 base; the INT8 ConvRot variant has separate numerical conditioning-parity evidence.
 
+### Three-encoder teacher-conditioning cosine
+
+The original matched three-encoder comparison reported these mean cosine similarities against the official Qwen3-VL-32B NVFP4/AWQ conditioning reference:
+
+| Encoder | Cosine similarity to official reference |
+|---|---:|
+| Official Qwen3-VL-32B NVFP4/AWQ reference | `1.000000000000000` (identity baseline) |
+| Recovered Qwen3-VL-8B + ARA + 4096-to-5120 adapter | `0.938678461010568` |
+| Physical pruned-24 Qwen3-VL-32B-derived INT8 ConvRot + balanced ARA | `0.9404705529707683` |
+
+These are text-conditioning diagnostics from the original three-encoder comparison. They are not visual-quality, prompt-adherence, or video-equivalence scores. Details: `evidence/three_encoder_teacher_cosine.json`.
+
 ### Recovered 8B BF16 versus INT8 ConvRot conditioning parity
 
 For one fixed seven-token prompt, the recovered 8B BF16 and INT8 ConvRot variants produced conditioning tensors with shape `[1, 7, 5120]`. The output tensors were flattened and compared with cosine similarity:
@@ -79,7 +91,7 @@ For one fixed seven-token prompt, the recovered 8B BF16 and INT8 ConvRot variant
 | Mean absolute difference | `0.015660330653190613` |
 | Maximum absolute difference | `0.6452102661132812` |
 
-This is a numerical conditioning-parity diagnostic for one prompt. It is not a visual-quality score, a prompt-adherence score, or proof that the INT8 variant produces identical video results. Full details are in `evidence/release_loader_smoke.json`.
+This is a separate numerical conditioning-parity diagnostic for one prompt. It is not a visual-quality score, a prompt-adherence score, or proof that the INT8 variant produces identical video results. Full details are in `evidence/release_loader_smoke.json`.
 
 The requested hard cuts at 3 and 7 seconds did not pass for any encoder. Read `evidence/cut_diagnostics.json` before using the showcase as prompt-adherence evidence.