Update weights

README.md

@@ -21,6 +21,12 @@ tags:
 
 # Standard One 3B (LoRA adapter)
 
+> **Updated weights (v2, 2026-09-26).** If you downloaded this adapter 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 3B
 LoRA adapter and a merge recipe; serving requires a merged checkpoint and the server code.
@@ -147,7 +153,7 @@ Full report: [`docs/BENCHMARKS.md`](docs/BENCHMARKS.md).
 ## 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** (as published in `StandardThinking/StandardOne-3B`): merging this adapter into the base changes **182 tensors**, none outside the language-model projections, maximum absolute weight change **0.0023**.
 - **Serving details:** native chat-template wording, no system prompt, 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.
 
@@ -163,18 +169,17 @@ quick-start guide live in `StandardThinking/StandardOne-8B`.
 
 ## Training data
 
-Trains on the identical mixture as `StandardThinking/StandardOne-8B-LoRA` — 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
+Trains on the same data sources as `StandardThinking/StandardOne-8B-LoRA`, 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,
+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.
 

SHA256SUMS

@@ -1,9 +1,9 @@
 1495e1e757ef4d0925a2350563cf5754bb23c51701a8ec4fb3c5cdcbedae6747  LICENSE
 caa6c931be76b0a3ed8d4901f520e3d71010ffbabe00cdd6a3de56563ffd26a3  NOTICE
-2207c0ff6402b9a3244964fc4b604da9e49ac73126aed53fd2785d2916c91200  README.md
-43b99a646a535b15e0f8bceebe2cfff03dd8cc519f5e21f68856b885657d7179  adapter_config.json
-7bc8bfff4be52e0c9c6f605faf1eebc5e8a966ce103793c7f6970e29056ef5d3  adapter_model.safetensors
-868cb61534ddc6f57b8718113c54391b2d7fae46d9b72b6ae59b3c96d4994d2c  docs/BENCHMARKS.md
+14ec17438881a77f2c305357854f35c64f516899894bb270d4609f6bbad0b374  README.md
+0d617456701ecb5bfb91d9fef119c3cfa9ce1f3d0c26a39d71893402c4928f3e  adapter_config.json
+a8e3eb341e27c1a49a282e327c2a2038906abb0eee771e80debbb4a4c45f7afc  adapter_model.safetensors
+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

adapter_config.json

@@ -32,13 +32,13 @@
   "rank_pattern": {},
   "revision": "b6d637bef2393152b3da2b2fde72eecdee30557e",
   "target_modules": [
-    "q_proj",
     "v_proj",
+    "up_proj",
     "down_proj",
+    "k_proj",
     "o_proj",
     "gate_proj",
-    "k_proj",
-    "up_proj"
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc8bfff4be52e0c9c6f605faf1eebc5e8a966ce103793c7f6970e29056ef5d3
+oid sha256:a8e3eb341e27c1a49a282e327c2a2038906abb0eee771e80debbb4a4c45f7afc
 size 135113048

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