v3 card: correct the long-document and JevBench hard numbers (clean re-run of the released weights)

README.md

@@ -56,8 +56,8 @@ graph, and returns a calibrated distribution for each question at once. In pract
 | Areas: Knowledge / Language / Retrieval / Tools / Arts | 25.2 / 44.2 / 59.7 / 60.3 / 19.8 | 30.3 / 49.5 / 63.3 / 79.8 / 36.5 |
 | HoVer, multi-hop claim verification (DI) | 62.7 | 63.9 |
 | BRIGHT, reasoning-heavy retrieval over long documents, ~12k tokens per request (DI) | 25.7 | 23.9 |
-| Decision hidden in a long document (our set, 150 items) | 82.00 | 88.00 |
-| JevBench public: easy / original / hard (48 / 72 / 111 items) | 100.00 / 98.61 / 63.96 | 100.00 / 98.61 / 60.36 |
+| Decision hidden in a long document (our set, 150 items) | 82.00 | 85.33 |
+| JevBench public: easy / original / hard (48 / 72 / 111 items) | 100.00 / 98.61 / 63.96 | 100.00 / 98.61 / 63.96 |
 
 Decision Index rows (DI) are chance-corrected skill scores (0 = random guessing, 100 = perfect) from our own runs of the public
 0.3 suite with the official kit, all 140,178 scoreable requests; every benchmark of both runs is in [standardone-3b-sh-v2](https://huggingface.co/datasets/StandardThinking/StandardOne-SH-decision-index/tree/main/runs/standardone-3b-sh-v2)

SHA256SUMS

@@ -1,5 +1,5 @@
 1495e1e757ef4d0925a2350563cf5754bb23c51701a8ec4fb3c5cdcbedae6747  LICENSE
-e9b0729b5f196d2dd66ff424a18e02d7d8b12db6235ccb838d004416a40b069e  README.md
+320de6b44809039797794661b79d1ffd7ad7d96447f2fa3184af8f4010521843  README.md
 331b249682cd52226c50e533f59825184997f3b31f9a62b2c3fea940db6999c5  SYSTEM_PROMPT.txt
 e62f05da25555a4c109d0f413eb673d328fcc40f7c82537c61631611f6954372  chat_template.jinja
 3208d5b86b4ce169d39302f52944f8898e42c6917aab121524bd54cae5af9cb0  config.json
@@ -9,7 +9,7 @@ e0923390059f84a9180b00e5501778acc45ea9856cd7f2fd68208b360927c677  generation_con
 55641440eb385d8bc83a319b0a92f60fe45e6aef4b6992245eee91142237786e  model.safetensors.index.json
 d15587c57574d2a92c66ff2552c6db5173d4c440ad47f7454dc51bad0ecaeb59  params.json
 ece2373c2ae391bce18785a1810543bc6173a1f28b6767cffab2c35dbea5f002  processor_config.json
-535a89c61b8551783e056c09f5111df116823b2ea107ca18d260d64e78e997ee  release-manifest.json
+a48416ec35f1e50f5add103b1902c6dbb8b1380aa9ee73ace4b9173ed89ea30f  release-manifest.json
 0a5c981e8c5c6f8886ee007a6d4543a0be6b221cb9ca32a8709384a4c6fc8cbb  special_tokens_map.json
 600bb27946565481ecf51ba8aee252e49b9a68507866080ac9c30185bb312843  tekken.json
 d5f6046775b112f0e2d456ee9dba450684ab964fe5c4e231599bdc6773028135  tokenizer.json

release-manifest.json

@@ -34,17 +34,17 @@
  "prompt_format": "chat template with an empty default system message (SH_SYSTEM_PROMPT=none)",
  "release": "StandardOne-3B-SH",
  "evaluation": {
-  "engine": "Standard One engine (SGLang fork ad26e8b179), 1 x AMD Instinct MI350X, 2026-10-13",
+  "engine": "Standard One engine (SGLang fork ad26e8b179), 1 x AMD Instinct MI350X, 2026-10-13, released weights (agrees with production on 1,427 of 1,431 parity questions)",
   "engine_clean_accuracy": {
-   "internal-eval-v1.heldout": 84.0,
-   "internal-eval-hardproxy-v1.heldout": 38.83,
+   "internal-eval-v1.heldout": 85.33,
+   "internal-eval-hardproxy-v1.heldout": 38.33,
    "internal-eval-v2-realistic.heldout": 89.17,
    "jevbench-easy": 100.0,
    "jevbench-original": 98.61,
-   "jevbench-hard": 60.36,
-   "longctx-dev": 88.0,
-   "winogrande-dev": 91.19,
-   "repair5k-validation-policy-judgment": 56.5
+   "jevbench-hard": 63.96,
+   "longctx-dev": 85.33,
+   "winogrande-dev": 91.59,
+   "repair5k-validation-policy-judgment": 57.0
   },
   "decision_index_0.3_public_index": 51.53,
   "decision_index_note": "self-scored with the official kit (apolinario/decision-index), all 140,178 scoreable requests"