Upload README.md with huggingface_hub

README.md

@@ -37,6 +37,26 @@ portable option and are what runs on Android.
 \*Mac arm64, single process, median of 10 — a reference point for relative cost
 only, not a device number (torch eager fp32 on the same machine: 34.4 ms).
 
+### Checked in the task's own units
+
+Correlation is a first filter, and on an embedding it is a weak one: a build can read
+0.999 against eager and still move an answer, because what decides is whether the error is
+smaller than the gap between the answer a query gets and the runner-up.
+
+The test is **near-duplicate retrieval** over 52 photographs, each also present centre-cropped to 90% and re-encoded as JPEG. Every item has one obviously
+correct nearest neighbour, and each build has to find it.
+
+| build | correct neighbour kept | worst score shift | budget spent |
+|---|---|---|---|
+| fp32 | 104 of 104 | 0.0015 | 5% |
+| fp16 | 104 of 104 | 0.0015 | 5% |
+| Core ML (fp16, iOS) | 104 of 104 | 0.0083 | 28% |
+
+The closest decision eager makes on this set is **0.0298**, and the bar is half of
+it. An earlier version of this card cleared int8 on "cosine similarity of the embeddings",
+which is correlation wearing a task metric's clothes — it never asked whether a retrieval
+answer moved.
+
 ## Verification (executorch 1.4.0, torch 2.13.0)
 
 Parity is measured against the fp32 eager model on real image input; `corr` is