docs(accuracy): publish phase 4 benchmark evidence

2026-08-02 05:10:05 +02:00
parent 70fb4b94e5
commit f41392a415
34 changed files with 25672 additions and 8 deletions
@@ -0,0 +1,6 @@
+{
+  "model_inference_executed": false,
+  "reason": "The reference harness performs deterministic evaluator arithmetic only. GPU latency, VRAM, throughput and failure-rate gates require the real active model.",
+  "schema_version": 2,
+  "status": "not_evaluable"
+}