Clarify live demo and align DecisionBench with official runner

README.md

@@ -33,18 +33,16 @@ model-index:
     dataset:
       type: Hanno-Labs/decision-bench
       name: DecisionBench 1.0 (23,900 decisions)
+      split: eval
     metrics:
     - type: accuracy
-      name: Accuracy (%, full coverage; expanded token budget for 251 rows)
-      value: 78.3
+      name: Accuracy (%, official runner; all 23,900 rows, no errors or truncation)
+      value: 78.05
     - type: accuracy
-      name: Accuracy (%, default 64k budget; failed rows count as incorrect)
-      value: 77.4
-    - type: accuracy
-      name: Accuracy (%, 20,959 rows with no detected source-text overlap; full coverage)
-      value: 78.0
+      name: Accuracy (%, official runner; 20,959 rows with no detected source-text overlap)
+      value: 77.73
     source:
-      name: AgentBull release evaluation (2026-09-29)
+      name: AgentBull official-runner evaluation (2026-09-30)
       url: https://huggingface.co/AgentBull/bongard-mini#benchmarks
   - task:
       type: zero-shot-classification
@@ -93,6 +91,21 @@ built on the **T5 encoder–decoder** architecture of **T5Gemma 2 4B-4B**. Give
 or images, along with questions and candidate answers or actions. It returns a probability
 distribution for each question without generating text.
 
+**Read once. Judge in parallel.**
+
+[Try the live demo](https://huggingface.co/spaces/AgentBull/bongard-mini) ·
+[Get started locally](#quick-start) · [Code & runtime](https://github.com/AgentBull/bongard/tree/main) ·
+[Design](#one-reading-many-decisions) · [Benchmarks](#benchmarks) · [Examples](#judgments-across-situations)
+
+In the live demo's **Playground**, choose an example, edit the **Input** and the questions under
+**Questions & settings**, then click **Run** to get new probabilities. The demo runs on Hugging Face
+ZeroGPU: anonymous quota is limited, and signing in provides more quota. For local execution, use
+the [quick start](#quick-start) below. The game GIFs below and the examples on the website are
+**recorded outputs**; use the live demo to try your own input.
+
+Bongard-mini is trained on judgments, semantic relationships and action outcomes. The same model
+can read a customer conversation, compare an invoice with an order, or judge an agent's next action.
+
 ## Game recordings
 
 | 2048 — 4096 tile, 55,140 final score | Tetris — consecutive line clears |
@@ -114,15 +127,6 @@ The model receives a text description of the scene every 0.2 seconds and chooses
 `turn_right` or `fire`. Across 32 episodes capped at 30 seconds, it averaged 10.25 kills, with a best
 of 20. The GIF shows an excerpt, with probabilities beside the action.
 
-Bongard-mini is trained on judgments, semantic relationships and action outcomes. The same model
-can read a customer conversation, compare an invoice with an order, or judge an agent's next action.
-
-**Read once. Judge in parallel.**
-
-[Try the live demo](https://huggingface.co/spaces/AgentBull/bongard-mini) ·
-[Code & runtime](https://github.com/AgentBull/bongard/tree/main) · [Quick start](#quick-start) ·
-[Design](#one-reading-many-decisions) · [Benchmarks](#benchmarks) · [Examples](#judgments-across-situations)
-
 ## Intuition is learned
 
 An experienced player sees a promising move. A reader catches irony. Such judgments draw on learned
@@ -303,45 +307,66 @@ print(response["answers"]["damaged"]["noul"])
 
 ## Benchmarks
 
-Release evaluation: **2026-09-29**, on one NVIDIA RTX PRO 6000 in BF16.
-These are our measurements on the splits and protocols below.
+DecisionBench was evaluated with its **official runner on 2026-09-30**. The other release
+evaluations below are from **2026-09-29**. Measurements use one NVIDIA RTX PRO 6000 in BF16,
+with the splits and protocols stated below.
 
 | Benchmark | Evaluation scope | Bongard-mini |
 |---|---|---|
-| [DecisionBench 1.0](https://huggingface.co/datasets/Hanno-Labs/decision-bench) | All 23,900 decisions, 43 tasks, 2–255 candidates | **78.3% accuracy**; **78.0%** on the 20,959 rows with no detected source-text overlap with training data |
+| [DecisionBench 1.0](https://huggingface.co/datasets/Hanno-Labs/decision-bench) | Official runner; `eval` split, all 23,900 decisions, 43 tasks, 2–255 candidates | **78.05% accuracy**; **77.73%** on the 20,959 rows with no detected source-text overlap with training data |
 | [JevBench v1.4](https://github.com/fstandhartinger/jevbench) | 231 public decisions: easy / standard / hard | **100% / 97.2% / 57.7% accuracy** |
 | [typed-decisions](https://huggingface.co/datasets/LocalLLaMA/typed-decisions) | Test split: 400 cases, 2,000 decisions; zero-shot workflows | **59.4% accuracy**, 0.518 soft accuracy, 0.256 KL, 0.132 Brier |
 | [ImajevBench v2.0-lite](https://huggingface.co/datasets/mohit67890/imajev-bench) | Dev + calibration: 254 items with public gold | **66.9% accuracy**; chance 26.5% |
 | [behavior-benchmark](https://huggingface.co/datasets/respanai/behavior-benchmark) | Every trace; present / absent / not observable | **0.458 / 0.668 F1** for `present`, core / multilingual |
 | Fair-chance probes | 18 kinds, including coins, dice, lotteries and tie-breaks | **0.0009 mean KL** from the uniform distribution; lower is better |
 
-**How to read these results:** DecisionBench's 78.3% result answers every row after increasing the
-request token budget for the 251 longest rows. At the default 64k-token budget, those rows fail and
-count as incorrect: accuracy is **77.4%**. The overlap-filtered 78.0% result uses full coverage.
+**How to read these results:** DecisionBench uses its own runner
+(`jobs/run_system_one_http_eval.py` at `9a6328e`) against `bongard serve` at `ea57853`, through
+the System One HTTP contract, one request at a time. Serving limits were **262,144 tokens per
+request** and **131,072 tokens per sequence**, with up to **255 candidates**. All 23,900 rows
+returned answers, with **no errors or input truncation**. The
+[official run, summary and manifest](https://huggingface.co/datasets/AgentBull/bongard-mini-evals/tree/main/decisionbench-official)
+are public. Of these rows, 2,941 have detected source-text overlap with training data; the remaining
+20,959 score 77.73%.
+
+An earlier custom-harness run remains in the
+[evaluation repository](https://huggingface.co/datasets/AgentBull/bongard-mini-evals#decisionbench).
+It sent 3,042 binary rows as two-option Choice questions, whereas the official runner sends Noul
+questions. Its scores belong to that earlier protocol and are not the headline result above.
+
 JevBench scores cover its public questions. For typed-decisions, the gold is a teacher probability
 distribution, so its metrics measure agreement with that teacher. ImajevBench uses direct option
 scoring with an `unknown` option and averages all cyclic option orders.
 
 ### DecisionBench comparison
 
-![DecisionBench 1.0 accuracy comparison across selected models](assets/decisionbench.png)
+| Selected systems | Accuracy |
+|---|---:|
+| Imajev-4B | 79.7% |
+| **Bongard-mini** | **78.05%** |
+| Winnow-12B | 76.7% |
+| Jev 1.13 | 72.0% |
+| DeepSeek V4.1 Flash | 71.0% |
+| GPT-5.6 Luna | 69.9% |
 
-Comparison snapshot from the [DecisionBench leaderboard](https://huggingface.co/spaces/Hanno-Labs/decision-bench-leaderboard),
-2026-09-29. Reference model scores are published leaderboard results; Bongard-mini is our full-coverage
-evaluation on the same rows and gold labels, with the token-budget and overlap qualifications above.
+Bongard-mini ranks fourth among the 61 systems in the full comparison. Reference scores are a
+2026-09-29 snapshot of the [DecisionBench leaderboard](https://huggingface.co/spaces/Hanno-Labs/decision-bench-leaderboard).
+Bongard-mini is our 2026-09-30 official-runner evaluation, with the serving limits and source-text
+overlap qualifications above. This table lists selected systems, rather than every leaderboard entry.
 
 ### Bongard and Jev, by task and measure
 
 | Evaluation | Bongard-mini | Jev 1.13 |
 |---|---:|---:|
-| DecisionBench accuracy, all 23,900 decisions | **78.3%** | 72.0% |
+| DecisionBench accuracy, official runner, all 23,900 decisions | **78.05%** | 72.0% |
 | typed-decisions top-label agreement, 2,000 decisions | 59.4% | **72.7%** |
 | typed-decisions KL from the teacher, lower is better | **0.256** | 1.442 |
 | typed-decisions Brier score, lower is better | **0.132** | 0.148 |
 
 Jev matches the teacher's top label more often on typed-decisions. Bongard's full distributions
-are closer to the teacher's under KL and Brier. Reference scores come from the dataset cards and
-leaderboards on 2026-09-29. Bongard's [per-item predictions](https://huggingface.co/datasets/AgentBull/bongard-mini-evals)
+are closer to the teacher's under KL and Brier. These measures establish agreement with the teacher;
+calibration against observed outcomes needs a separate evaluation. Reference scores come from the dataset
+cards and leaderboards on 2026-09-29. Bongard's [per-item predictions](https://huggingface.co/datasets/AgentBull/bongard-mini-evals)
 let you inspect the decisions behind the scores.
 
 ### Inference speed