Publish camera-ready metadata reproduction and validation scope

README.md

@@ -128,8 +128,12 @@ The API returns a wrapper object with `id`, `object`, `created`, `model`, and `r
 
 ## Diagnose your own model
 
-Use the [complete KoEVD own-model workflow](https://github.com/KETI-NLP/KoEVD/blob/main/docs/OWN_MODEL_GUIDE.md) to generate your model’s responses, measure Task 1–5 behavior, and produce HTML/JSON/CSV reports of metadata-specific strengths, weaknesses, strategies and source-matched tool-selection gaps. The current GitHub source adds this pipeline; the original v0.1.0 code tag does not include it. A subsequent [live B200 pipeline test](https://github.com/KETI-NLP/KoEVD/blob/main/docs/PIPELINE_VALIDATION_RESULTS.md) completed 40/959 actual generation requests with unmodified code. It also found batch-dependent strategy outputs and concerning safety judgments; execution success does not establish measurement accuracy.
+Use the [complete KoEVD own-model workflow](https://github.com/KETI-NLP/KoEVD/blob/main/docs/OWN_MODEL_GUIDE.md) to generate your model’s responses, measure Task 1–5 behavior, and produce HTML/JSON/CSV reports of metadata-specific strengths, weaknesses, strategies and source-matched tool-selection gaps. The current GitHub source adds this pipeline; the original v0.1.0 code tag does not include it. A subsequent [live B200 pipeline test](https://github.com/KETI-NLP/KoEVD/blob/main/docs/PIPELINE_VALIDATION_RESULTS.md) completed 40 smoke requests and 959 expanded generation requests with unmodified code. It also found batch-dependent strategy outputs and concerning safety judgments; execution success does not establish measurement accuracy.
 
 ## Observed batch sensitivity — 2026-09-15
 
 The [live pipeline test](https://github.com/KETI-NLP/KoEVD/blob/main/docs/PIPELINE_VALIDATION_RESULTS.md) completed inference, but strategy sets and raw outputs differed at batch sizes 2 and 4 for 5/191 responses (2.62%). One change was `e_humour` to `unsafe`; unsafe-marker counts were 22 versus 23. The cause is unresolved and no runtime patch is established. Record batch size, input ordering, precision and environment; exact batch invariance is not guaranteed. The unsafe marker is a measurement proxy and should not automatically replace the separate safety classifier output.
+
+## Later reproduction scope — 2026-09-15
+
+A separate B200 check reproduced the assistant-safety classifier’s historical raw outputs and labels on all 532 original validation inputs at batches 2, 4, and 32, retaining macro/micro F1 0.9981/0.9981 and the same single error. It did not rerun response-strategy validation F1. On 191 new generated responses, suspicious all-safe safety outputs and 5/191 batch-dependent strategy label sets remain unresolved; no new human gold or new-response F1 was established. See the [reproduction scope](https://github.com/KETI-NLP/KoEVD/blob/main/docs/REPRODUCIBILITY.md). Earlier operational-test statements above describe their original 12/96-candidate sample, not this subsequent check.

manifest.json

@@ -24,8 +24,8 @@
     },
     {
       "path": "README.md",
-      "bytes": 8805,
-      "sha256": "7f9cb712b7b9b039308ea7b8ab96ed50fa43a80f2f9ee02b6e3dbca39f702866"
+      "bytes": 9555,
+      "sha256": "b0ef79a9e60705f27cfa1f847ecc5825fcbfff07d470a0b8fe09a9396cef5742"
     },
     {
       "path": "adapter_config.json",
@@ -87,5 +87,6 @@
       "bytes": 665,
       "sha256": "47bfa3e7727312946b29ac10d6dd0672d63cf7815b2a160b9523872040d2e536"
     }
-  ]
+  ],
+  "documentation_update": "2026-09-15 camera-ready clarification; canonical data and model weights unchanged"
 }