Update weights

MERGE_REPORT.json

@@ -1,15 +1,15 @@
 {
   "snapshot": "mistralai/Ministral-3-3B-Instruct-2512-BF16@b6d637bef2393152b3da2b2fde72eecdee30557e",
-  "adapter": "StandardOne-3B-LoRA (training run hard25-3b-r1)",
-  "adapter_sha256": "7bc8bfff4be52e0c9c6f605faf1eebc5e8a966ce103793c7f6970e29056ef5d3",
+  "adapter": "StandardOne-3B-LoRA v2 (training run r5-3b)",
+  "adapter_sha256": "a8e3eb341e27c1a49a282e327c2a2038906abb0eee771e80debbb4a4c45f7afc",
   "changed_params": 182,
   "unchanged_params": 276,
   "changed_outside_lm_projections": [],
-  "max_abs_delta": 0.0022978782653808594,
+  "max_abs_delta": 0.002337932586669922,
   "changed_sample": [
     [
       "model.language_model.layers.0.self_attn.q_proj.weight",
-      0.0011186599731445312
+      0.0010986328125
     ],
     [
       "model.language_model.layers.0.self_attn.k_proj.weight",
@@ -17,19 +17,19 @@
     ],
     [
       "model.language_model.layers.0.self_attn.v_proj.weight",
-      0.0014190673828125
+      0.001434326171875
     ],
     [
       "model.language_model.layers.0.self_attn.o_proj.weight",
-      0.001007080078125
+      0.00103759765625
     ],
     [
       "model.language_model.layers.0.mlp.gate_proj.weight",
-      0.00202178955078125
+      0.00200653076171875
     ],
     [
       "model.language_model.layers.0.mlp.up_proj.weight",
-      0.0017843246459960938
+      0.00177001953125
     ],
     [
       "model.language_model.layers.0.mlp.down_proj.weight",
@@ -37,7 +37,7 @@
     ],
     [
       "model.language_model.layers.1.self_attn.q_proj.weight",
-      0.001434326171875
+      0.00146484375
     ]
   ],
   "file_sha256": {
@@ -45,8 +45,8 @@
     "chat_template.jinja": "0701cfbdc2b7d44fdbad104dff604faee4b0543e8247624568777fe465746f9b",
     "config.json": "c4446cf970fefd8b65f2e3119c30d406ea7026dca362dfb319c9aa08643131c3",
     "generation_config.json": "e0923390059f84a9180b00e5501778acc45ea9856cd7f2fd68208b360927c677",
-    "model-00001-of-00002.safetensors": "8a02fdf56e2c3fdf75b303a1c617ed8bebe06d7e934e7ef56af3689a7a2552a5",
-    "model-00002-of-00002.safetensors": "1d8099875a6e4466dace9ceab20c38ffee02903dbb2acee9d5b0565b6e64da2a",
+    "model-00001-of-00002.safetensors": "7029a24151316b12d84b0e666c6af7d46bfe07e9549d59e513bb34afabb43073",
+    "model-00002-of-00002.safetensors": "ad184b56624eaca81a22c7fb7bef034edd25bd435cfb173a76d0db1b2c67ff2b",
     "model.safetensors.index.json": "55641440eb385d8bc83a319b0a92f60fe45e6aef4b6992245eee91142237786e",
     "params.json": "d15587c57574d2a92c66ff2552c6db5173d4c440ad47f7454dc51bad0ecaeb59",
     "processor_config.json": "ece2373c2ae391bce18785a1810543bc6173a1f28b6767cffab2c35dbea5f002",
@@ -55,5 +55,5 @@
     "tokenizer.json": "d5f6046775b112f0e2d456ee9dba450684ab964fe5c4e231599bdc6773028135",
     "tokenizer_config.json": "f59f7294e4f26383d0ea93840fe21cf197784be0842a8301a0343e8c34ed0d6d"
   },
-  "seconds": 26.7
+  "seconds": 25.9
 }

README.md

@@ -27,6 +27,12 @@ tags:
 
 # Standard One 3B
 
+> **Updated weights (v2, 2026-09-26).** If you downloaded this model before, download it again or pin
+> `revision="v2"`. Earlier versions stay available under the tags `v1` and `v1.1`.
+> The benchmark figures and the serving temperature on this card are still those of v1.1 and are being updated for v2.
+
+**Version:** v2
+
 Standard One scores a bounded set of answers for a supplied scenario and returns probabilities through
 `POST /v1/systemone`. It does not generate free-form response text. This repository contains the merged
 BF16 3B checkpoint; the server code is in [StandardOne-8B](https://huggingface.co/StandardThinking/StandardOne-8B).
@@ -192,7 +198,7 @@ A JevBench v1.4.1 run has been requested; the sealed-set result is not yet avail
 ## Model details
 
 - **Base model:** `mistralai/Ministral-3-3B-Instruct-2512-BF16`, revision `b6d637bef2393152b3da2b2fde72eecdee30557e` (Apache-2.0).
-- **Adapter:** LoRA r=16, α=32, dropout 0, on `q_proj k_proj v_proj o_proj gate_proj up_proj down_proj` of the language-model projections only (vision tower and multimodal projector excluded), **24,707,072** trainable parameters, PEFT 0.21.0. Adapter file `adapter_model.safetensors`, 135,113,048 bytes, sha256 `7bc8bfff4be52e0c9c6f605faf1eebc5e8a966ce103793c7f6970e29056ef5d3`.
+- **Adapter:** LoRA r=16, α=32, dropout 0, on `q_proj k_proj v_proj o_proj gate_proj up_proj down_proj` of the language-model projections only (vision tower and multimodal projector excluded), **24,707,072** trainable parameters, PEFT 0.21.0. Adapter file `adapter_model.safetensors`, 135,113,048 bytes, sha256 `a8e3eb341e27c1a49a282e327c2a2038906abb0eee771e80debbb4a4c45f7afc`.
 - **Merged BF16 checkpoint:** merging the adapter into the base changed **182 tensors**, none of them outside the language-model projections, maximum absolute weight change **0.0023**.
 - **Serving details:** native chat-template wording, served without a system prompt, at a fixed temperature (T = 1.55, fitted on held-out calibration data); served model name `standard-one-3b` behind stock SGLang 0.5.20 via `jev-adapter` (`POST /v1/systemone`); single, caller-supplied option order, no rotation ensemble; 8,192-token context.
 
@@ -207,9 +213,13 @@ The server code and full quick-start guide live in `StandardThinking/StandardOne
 
 ## Training data
 
-Trains on the identical mixture as `StandardThinking/StandardOne-8B` — same cohorts, same row counts, same overlap-audit result, not a reduced subset. Training data spans document and field normalisation, judge/routing and answer-adequacy, stated-distribution probability, verification/scoring, adequacy-rubric style, abstention and robustness (paraphrase, trap, hard natural-language), and game- and Tetris board-state cohorts — every row is synthetic and solver-generated (deterministic generators with visible checkers; a subset was teacher-reviewed), licensed Apache-2.0 (ours); the JevBench public tiers used only for evaluation carry MIT. Full per-cohort breakdown: [`docs/BENCHMARKS.md`](docs/BENCHMARKS.md#training-data-provenance).
+Trains on the same data sources as `StandardThinking/StandardOne-8B`, not a reduced subset. Training data is synthetic and format-augmented decision data plus decision items converted from public
+datasets (listed below); the JevBench public tiers used only for evaluation carry MIT. Full per-cohort breakdown: [`docs/BENCHMARKS.md`](docs/BENCHMARKS.md#training-data-provenance).
+
+Public datasets used (train splits where the dataset has one; licence as stated by each dataset; labels come from the
+datasets, distractor options are generated by code): SQuAD 2.0 (CC BY-SA 4.0), ARC (CC BY-SA 4.0), BoolQ (CC BY-SA 3.0), CommonsenseQA (MIT), HellaSwag (MIT), Banking77 (CC BY 4.0), Bias in Bios (MIT), Bitext customer support (CDLA-Sharing-1.0), CLINC150 (CC BY 3.0), Amazon Counterfactual (CC BY 4.0), DBpedia-14 (CC BY-SA 3.0), Dolly 15k (CC BY-SA 3.0), GoEmotions (Apache-2.0), MASSIVE (CC BY 4.0), Twitter Financial News Sentiment (MIT), HelpSteer3 (CC BY 4.0), HelpSteer2 (CC BY 4.0), 2WikiMultihopQA (Apache-2.0), HotpotQA (CC BY-SA 4.0), MuSiQue (CC BY 4.0), QASC (CC BY 4.0), DROP (CC BY-SA 4.0), GSM8K (MIT), TempReason (CC BY-SA 3.0), MultiNLI (OANC / CC BY-SA 3.0 / CC BY 3.0), PAWS (Google terms, free for any purpose), PAWS-X (Google terms, free for any purpose), SNLI (CC BY-SA 4.0), WANLI (CC BY 4.0), ContractNLI (CC BY 4.0), CUAD (CC BY 4.0), ShARC (CC BY-SA 3.0), Jailbreak classification (Apache-2.0), Prompt injections (Apache-2.0), Aegis AI Content Safety 2.0 (CC BY 4.0), Jigsaw Toxic Comment Classification (mirror of the Kaggle data) (CC0 (data); comment text CC BY-SA 3.0 (Wikipedia)), Measuring Hate Speech (CC BY 4.0), Image safety classes (MIT). Upstream ids and the cohort each one feeds: [`docs/BENCHMARKS.md`](docs/BENCHMARKS.md#training-data-provenance).
 
-An exact-text overlap audit against the public JevBench tiers found 0 exact scenario matches and 181 exact instruction matches — rows in two adequacy-rubric cohorts whose entire instruction field, a generic 58-character adequacy question, is byte-identical to one public hard-tier instruction (0.05 % of the 382,576-row training mixture). These rows are kept and disclosed here rather than regenerated, since the overlap is limited to one rubric question's wording and never touches a scenario or an answer.
+An exact-text overlap audit against the public JevBench tiers found 0 exact scenario matches and 181 exact instruction matches — rows in two adequacy-rubric cohorts whose entire instruction field, a generic 58-character adequacy question, is byte-identical to one public hard-tier instruction (0.03 % of the 520,754-row training mixture). These rows are kept and disclosed here rather than regenerated, since the overlap is limited to one rubric question's wording and never touches a scenario or an answer.
 
 ## Limitations
 

SHA256SUMS

@@ -1,12 +1,12 @@
 1495e1e757ef4d0925a2350563cf5754bb23c51701a8ec4fb3c5cdcbedae6747  LICENSE
-6756de0e7de5d85d7f5b4ff2e5e75b4b74e2d2ad7f0addf5719e652ba53e15dc  MERGE_REPORT.json
+916927708f20ec40252055f98ad7f09f5dcfacadc31e99d85bcac19f285b7bad  MERGE_REPORT.json
 f10343f951ecb3a72670e12720de6e04d59e9cb872e84b2ceddd7d54853bb7e7  NOTICE
 372d9160e95493d1d8e5c94d82b12fb0693fd36e4a50f5206d287ee74f189046  QUICKSTART.md
-e97c6a7f38db1a9f5b2a1fe8ed128b60d5d0c48e87671b6f2a108f155d60cce8  README.md
+faf66b200ab0a00f0e7f7c7174af1996c45376d3e529ed08ea7582b232c1e602  README.md
 331b249682cd52226c50e533f59825184997f3b31f9a62b2c3fea940db6999c5  SYSTEM_PROMPT.txt
 0701cfbdc2b7d44fdbad104dff604faee4b0543e8247624568777fe465746f9b  chat_template.jinja
 c4446cf970fefd8b65f2e3119c30d406ea7026dca362dfb319c9aa08643131c3  config.json
-868cb61534ddc6f57b8718113c54391b2d7fae46d9b72b6ae59b3c96d4994d2c  docs/BENCHMARKS.md
+141067bb117600df9e09a46098e6a1f26e685ea5eab77f73b20352bce6d503d6  docs/BENCHMARKS.md
 96127670ad1e5bdd336a33118d6246330c27ac9e4fcb3f4f22767033809cd889  docs/assets/00-benchmark-card.png
 28c67a8c861f421fae5889af259d0850e7fb6eadb11f247adef72b94bf00b187  docs/assets/00-benchmark-card.svg
 7313f2b0645ee401d082572986dcee0c08d3daed1ae79fa650cfa685570ad7e2  docs/assets/02-latency-vs-qwen.png
@@ -25,12 +25,12 @@ dd888be78c0e32894cf04a8e3fbf8757e7218873668fa4443ba47c7c1c48b6dc  docs/assets/04
 7b9b1ee2f93166a817ead61bbc0f4c62984afe7d6c8affefd051007582d0a485  evidence/served-nosys-latency-idle-gpu.json
 5b217fe780b4c8c7cb292d57630b0f0a0bb5dcbe275f731272d6f0804cc14a68  evidence/served-nosys-original-report.json
 e0923390059f84a9180b00e5501778acc45ea9856cd7f2fd68208b360927c677  generation_config.json
-8a02fdf56e2c3fdf75b303a1c617ed8bebe06d7e934e7ef56af3689a7a2552a5  model-00001-of-00002.safetensors
-1d8099875a6e4466dace9ceab20c38ffee02903dbb2acee9d5b0565b6e64da2a  model-00002-of-00002.safetensors
+7029a24151316b12d84b0e666c6af7d46bfe07e9549d59e513bb34afabb43073  model-00001-of-00002.safetensors
+ad184b56624eaca81a22c7fb7bef034edd25bd435cfb173a76d0db1b2c67ff2b  model-00002-of-00002.safetensors
 55641440eb385d8bc83a319b0a92f60fe45e6aef4b6992245eee91142237786e  model.safetensors.index.json
 d15587c57574d2a92c66ff2552c6db5173d4c440ad47f7454dc51bad0ecaeb59  params.json
 ece2373c2ae391bce18785a1810543bc6173a1f28b6767cffab2c35dbea5f002  processor_config.json
-fa228b3ddc6db30e10a55b8b7039646572f53e66f96c04a416f34480e9415e54  release-manifest.json
+f9913e0d49fc053df656058d13af2523b6263f9396efad7a6fa06e7a121e1acf  release-manifest.json
 eef2a88a000d2ec294379755770c147327cb79d3d7278c711899bd36797d7a02  server/.gitignore
 1495e1e757ef4d0925a2350563cf5754bb23c51701a8ec4fb3c5cdcbedae6747  server/LICENSE
 0f1f023b916d38d7c12af3a71e09f5e82b819a7e156e4992118bb160ee63ede1  server/NOTICE

docs/BENCHMARKS.md

@@ -1,5 +1,8 @@
 # Standard One — full benchmark report
 
+> **Note.** The benchmark figures in this report are for v1.1 and are being updated for v2. The training-data provenance and
+> overlap-audit sections below already describe the v2 weights.
+
 This report covers both released systems, **Standard One 8B** (`StandardThinking/StandardOne-8B` / `-LoRA`) and
 **Standard One 3B** (`StandardThinking/StandardOne-3B` / `-LoRA`). It is our own measurement, not an official JevBench
 leaderboard score. The only comparisons in this report are: the untuned
@@ -280,9 +283,8 @@ and in `release-manifest.json`, identical for both candidates.
 
 ## Training data provenance
 
-The following cohort families make up the identical 34-cohort, 382,576-row training mixture used by
-both Standard One 8B and Standard One 3B. Every row is synthetic and solver-generated (deterministic generators with
-visible checkers; a subset was teacher-reviewed). No JevBench evaluation scenario appears in any
+The following cohort families make up the 46-cohort, 520,754-row training mixture used by
+both Standard One 8B and Standard One 3B. Apart from the public-dataset items listed below, every row is synthetic (deterministic generators with visible checkers; a subset was teacher-reviewed) or format-augmented. No JevBench evaluation scenario appears in any
 training cohort.
 
 | Cohort family | What it covers | Licence |
@@ -295,11 +297,57 @@ training cohort.
 | Abstention & robustness (`abstain`, `paraphrase`, `trap`, `hard-natural`) | Abstaining when the state does not settle the question, paraphrased and adversarial wording, harder natural-language decisions | Apache-2.0 (ours) |
 | Game & board-state (`games-text-train`, `games-harness-train`, `games-harness-multilingual`) | Othello, chess, tic-tac-toe, snake and graph-problem decisions | Apache-2.0 (ours) |
 | Tetris board-state (`games-text-train-tetris`, `games-harness-tetris`, `tetris-drought-train`) | Tetris-specific board-state decisions | Apache-2.0 (ours) |
+| Synthetic and format-augmented decision data (v2) | Decision items in varied layouts | Apache-2.0 (ours) |
+| Public-dataset decision items | Decision items converted from public datasets (table below) | Each dataset's own licence (table below) |
 | JevBench public tiers (evaluation only, not training) | Easy / standard / hard held-out accuracy measurement | MIT |
 
+Public datasets used (train splits where a dataset has one; CUAD: its single release file). Labels come from the datasets;
+distractor options and derived labels are generated by code. Licences as stated by each dataset; attribution to the dataset authors.
+
+| Dataset | Upstream id | Licence | Cohort |
+|---|---|---|---|
+| SQuAD 2.0 | `rajpurkar/squad_v2` | CC BY-SA 4.0 | `pub-abstain-v1` |
+| ARC | `allenai/ai2_arc` | CC BY-SA 4.0 | `pub-breadth-v1` |
+| BoolQ | `google/boolq` | CC BY-SA 3.0 | `pub-breadth-v1` |
+| CommonsenseQA | `tau/commonsense_qa` | MIT | `pub-breadth-v1` |
+| HellaSwag | `Rowan/hellaswag` | MIT | `pub-breadth-v1` |
+| Banking77 | `PolyAI/banking77` | CC BY 4.0 | `pub-classify-v1` |
+| Bias in Bios | `LabHC/bias_in_bios` | MIT | `pub-classify-v1` |
+| Bitext customer support | `bitext/Bitext-customer-support-llm-chatbot-training-dataset` | CDLA-Sharing-1.0 | `pub-classify-v1` |
+| CLINC150 | `clinc/clinc_oos` | CC BY 3.0 | `pub-classify-v1` |
+| Amazon Counterfactual | `mteb/amazon_counterfactual` | CC BY 4.0 | `pub-classify-v1` |
+| DBpedia-14 | `fancyzhx/dbpedia_14` | CC BY-SA 3.0 | `pub-classify-v1` |
+| Dolly 15k | `databricks/databricks-dolly-15k` | CC BY-SA 3.0 | `pub-classify-v1`, `safety-judge-v1` |
+| GoEmotions | `google-research-datasets/go_emotions` | Apache-2.0 | `pub-classify-v1` |
+| MASSIVE | `AmazonScience/massive` | CC BY 4.0 | `pub-classify-v1` |
+| Twitter Financial News Sentiment | `zeroshot/twitter-financial-news-sentiment` | MIT | `pub-classify-v1` |
+| HelpSteer3 | `nvidia/HelpSteer3` | CC BY 4.0 | `pub-judge-v1` |
+| HelpSteer2 | `nvidia/HelpSteer2` | CC BY 4.0 | `pub-judge-v1` |
+| 2WikiMultihopQA | `framolfese/2WikiMultihopQA` | Apache-2.0 | `pub-multihop-v1` |
+| HotpotQA | `hotpotqa/hotpot_qa` | CC BY-SA 4.0 | `pub-multihop-v1` |
+| MuSiQue | `dgslibisey/MuSiQue` | CC BY 4.0 | `pub-multihop-v1` |
+| QASC | `allenai/qasc` | CC BY 4.0 | `pub-multihop-v1` |
+| DROP | `ucinlp/drop` | CC BY-SA 4.0 | `pub-numeric-v1` |
+| GSM8K | `openai/gsm8k` | MIT | `pub-numeric-v1` |
+| TempReason | `tonytan48/TempReason` | CC BY-SA 3.0 | `pub-numeric-v1` |
+| MultiNLI | `nyu-mll/multi_nli` | OANC / CC BY-SA 3.0 / CC BY 3.0 | `pub-paraphrase-v1` |
+| PAWS | `google-research-datasets/paws` | Google terms, free for any purpose | `pub-paraphrase-v1` |
+| PAWS-X | `google-research-datasets/paws-x` | Google terms, free for any purpose | `pub-paraphrase-v1` |
+| SNLI | `stanfordnlp/snli` | CC BY-SA 4.0 | `pub-paraphrase-v1` |
+| WANLI | `alisawuffles/WANLI` | CC BY 4.0 | `pub-paraphrase-v1` |
+| ContractNLI | `stanfordnlp.github.io/contract-nli` | CC BY 4.0 | `pub-rules-v1` |
+| CUAD | `theatticusproject/cuad` | CC BY 4.0 | `pub-rules-v1` |
+| ShARC | `sharc-data.github.io` | CC BY-SA 3.0 | `pub-rules-v1` |
+| Jailbreak classification | `jackhhao/jailbreak-classification` | Apache-2.0 | `safety-judge-v1` |
+| Prompt injections | `deepset/prompt-injections` | Apache-2.0 | `safety-judge-v1` |
+| Aegis AI Content Safety 2.0 | `nvidia/Aegis-AI-Content-Safety-Dataset-2.0` | CC BY 4.0 | `content-safety-text-v1` |
+| Jigsaw Toxic Comment Classification (mirror of the Kaggle data) | `tasksource/jigsaw_toxicity` | CC0 (data); comment text CC BY-SA 3.0 (Wikipedia) | `content-safety-text-v1` |
+| Measuring Hate Speech | `ucberkeley-dlab/measuring-hate-speech` | CC BY 4.0 | `content-safety-text-v1` |
+| Image safety classes | `deepghs/nsfw_detect` | MIT | `content-safety-image-v1`, `content-safety-image-2d-v1` |
+
 ## Public-overlap audit and disclosure
 
-Run on the exact final 34-cohort, 382,576-row mixture that **both candidates train on**:
+Run on the 46-cohort, 520,754-row training data that **both candidates train on**:
 
 - **0 exact state matches** — no training row's state/scenario duplicates any public JevBench item.
 - **181 exact instruction matches**: `hardstyle-train-v1` (87 of 3,900 rows) and `hardstyle-train-v2`
@@ -307,13 +355,10 @@ Run on the exact final 34-cohort, 382,576-row mixture that **both candidates tra
   one public `jevbench-hard` instruction — a 58-character generic adequacy-rubric question ("does the
   response fully and correctly satisfy the request?"), reused as the complete instruction rather than
   as a substring.
-- 16 distinct shared word 8-grams (12 distinct phrases, 9,756 rows), all in three known families: the
-  rubric sentence above (also in `judge-realistic-train-v3`, `judge-multilingual-train-v1`,
-  `judge-proxy-v1`), an insurance "cancellation takes effect" boilerplate clause, and a "coverage
-  reviewer" claims-adjudication phrase.
-- All other 32 cohorts: 0 exact state and 0 exact instruction matches.
+- 24 distinct shared word 8-grams (20,400 rows), all in known families: the rubric sentence above (also in `judge-realistic-train-v3`, `judge-multilingual-train-v1`, `judge-proxy-v1` and the format-augmented cohort), an insurance "cancellation takes effect" boilerplate clause, a "coverage reviewer" claims-adjudication phrase, and generic contract boilerplate (for example "controlled by or under common control with") in one public-dataset cohort.
+- All other 44 cohorts: 0 exact state and 0 exact instruction matches.
 
-**These 181 rows are kept and disclosed here, not regenerated.** They are 0.05 % of the mixture, and
+**These 181 rows are kept and disclosed here, not regenerated.** They are 0.03 % of the mixture, and
 the exposure is limited to one hard-tier *question's* generic wording, never a *state* or an answer.
 
 ## Evidence file hashes

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a02fdf56e2c3fdf75b303a1c617ed8bebe06d7e934e7ef56af3689a7a2552a5
+oid sha256:7029a24151316b12d84b0e666c6af7d46bfe07e9549d59e513bb34afabb43073
 size 4995664864

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8099875a6e4466dace9ceab20c38ffee02903dbb2acee9d5b0565b6e64da2a
+oid sha256:ad184b56624eaca81a22c7fb7bef034edd25bd435cfb173a76d0db1b2c67ff2b
 size 2702576200

release-manifest.json

@@ -1,24 +1,26 @@
 {
   "release": "StandardOne-3B",
+  "version": "v2",
   "base_model": {
     "repo": "mistralai/Ministral-3-3B-Instruct-2512-BF16",
     "revision": "b6d637bef2393152b3da2b2fde72eecdee30557e"
   },
   "adapter": {
-    "source_run": "hard25-3b-r1",
-    "adapter_model_sha256": "7bc8bfff4be52e0c9c6f605faf1eebc5e8a966ce103793c7f6970e29056ef5d3"
+    "source_run": "r5-3b",
+    "adapter_model_sha256": "a8e3eb341e27c1a49a282e327c2a2038906abb0eee771e80debbb4a4c45f7afc"
   },
   "merge_report_summary": {
     "changed_params": 182,
     "unchanged_params": 276,
     "changed_outside_lm_projections": [],
-    "max_abs_delta": 0.0022978782653808594
+    "max_abs_delta": 0.002337932586669922
   },
   "serving": {
     "wording": "native",
     "system_prompt": null,
     "temperature": 1.55,
     "served_model_name": "standard-one-3b",
-    "engine": "SGLang 0.5.20"
+    "engine": "SGLang 0.5.20",
+    "note": "serving settings shown are those of v1.1; they are being re-fitted for v2"
   }
 }