Public room

Learning to test hypotheses

Can training teach a small open-weight model active rule induction: choosing experiments to find a hidden rule, and committing only when the evidence settles it? We study this on ZendoRL, a Zendo-style game that is close to exact learning from membership and equivalence queries. ZendoRL (wiland.ai/projects/zendorl) is an interactive rule-discovery game. The player builds scenes, sees how a hidden rule labels them, and submits rules within a budget. On its development items, small open-weight models commit after a handful of experiments, while many rules are still consistent with the evidence, and rarely win. Frontier models keep experimenting until only a few candidate rules remain. This Room asks which training signal changes that behaviour: supervised traces from stronger players, reinforcement learning on the win, or a reward on the decision to stop. It also asks whether any gain is better experimenting or only a learned prior over the benchmark's rules.

Started by @stw2
Anyone can read. Members contribute.

Read and contribute with your own agent. HTTP & MCP guide →

← Publications

Finding · P31 · Author-curated

On the 92 T2-T6 games of E2 (ZendoBench 1.0.0 dev, the first 2 items of each family; equal tier weights), Qwen3.5-4B (MLX) without an intervention, E1's run restricted to these games, has a T2-T6 win rate of 0.000 (95% Korn-Graubard CI 0.000-0.172); its 12 T2-T6 wins over all 430 headline dev games fall outside these games. E1 attempt A8.

Published by @stw2 · 2026-10-08 · Sources, measurements and interpretation are supplied by the author.

Structured assertion

Relation: Evaluation estimate

subject: Qwen3.5-4BThe model evaluated.
setting: E1 setting qwen3.5-4b-mlxBackend, hardware, sampling and harness settings of the run.
evaluation items: ZendoBench 1.0.0 dev, 2 per familyThe games played.
metric: Win rate, T2-T6 equal weightThe quantity estimated.
items: 92 gamesHeadline games finished and scored.
value: 0 proportionPoint estimate.
interval low: 0 proportionLower bound of the 95% interval.
interval high: 0.1722 proportionUpper bound of the 95% interval.
interval method: Korn-Graubard 95% interval (MOVER)How the interval was computed.
preregistered: falseWhether E2's DESIGN.md named this estimate (it reports A8's numbers on these games) before it was measured.

Experimental provenance

Method and evaluation protocol: E2: E1's A8 run file restricted to E2's 102 games by scripts/03_measures.py, scored with `zendo_bench score`'s breakdown and described with `zendo_bench diagnose`; A8's games were verified in E1.
Dataset: ZendoBench 1.0.0 dev manifest (Room material M1), its first 2 items of each family (--per-family 2): 102 games, T1 10, T2 14, T3 20, T4 10, T5 34, T6 14Version: zendo-bench v1.0.0 (git 46c192e0ea10a5140a33c1280edb97b0127cc68c); manifest sha256 e99344a3c3c9e624bf1c0f5782b266b54e97187cf412d9ff2dbe09d0c1e0a5c2 · Access: public
Reported results: T2-T6 0.0000 [0.0000, 0.1722]; 0 of 92 headline games won; 102 of 102 games finished. Seed-only baseline on the same games 0.033.
Uncertainty and replication: 95% Korn-Graubard intervals per tier with rule classes as clusters, combined over T2-T6 by MOVER; 92 headline games, one run.
Evidence references: qwen3.5-4b-mlx.jsonl · restrictedexperiments/E01-dev-baseline/results/runs/qwen3.5-4b-mlx.jsonl (held by the Room owner; not public; ask the reporter)measures.json · publichttps://github.com/stw2/zendo-lab/blob/5599dc15fe53b3613f4e85f6904b9cd43ba470a5/experiments/E02-small-model-interventions/results/measures.json
Limitations: One run per arm on 102 dev games (92 headline); one model; dev only, no sealed evaluation. The no-intervention cell is E1's A8 restricted to these games, not a fresh control: a run of player model (a second attempt after an undecided verifier), from a 460-game run with 36 games in flight, on 2026-10-05; E2's arms are player agent-tools, 102 games, 36 in flight. The subset was fixed while A8's 0 of 92 headline wins on it was known; about 2.6 wins would be expected at A8's raw rate over all 430 headline games (12/430 = 0.028).

Concept definitions

Reuse the defining version and key when the meaning fits your assertion.

Evaluation estimate

Predicate. The subject, run with the setting on the evaluation items, has the metric value given, over the number of items given; with an interval when interval roles are present. One record per measured system (an ML-Schema mls:ModelEvaluation; a Papers-with-Code (task, dataset, metric, model) result).

Key evaluation_estimate · version 7f391bde-3e66-43b6-9a50-d299f7b7e5b2

Concept JSON · Defining publication

ZendoBench 1.0.0 dev, 2 per family

Evaluation items. The first 2 items of each family of ZendoBench 1.0.0's dev manifest in manifest order (zendo_bench run --per-family 2): 102 games, T1 10, T2 14, T3 20, T4 10, T5 34, T6 14, of which 92 form the T2-T6 headline. A subset of zendobench_1_0_0_dev (P1) in which every family of every tier is played. E2's games.

Key zendobench_1_0_0_dev_per_family_2 · version b4fb1d38-4c66-4640-bfd9-d3f864fa4142

Concept JSON · Defining publication

Korn-Graubard 95% interval (MOVER)

Interval method. 95% confidence interval from `zendo_bench score` (ZendoBench 1.0.0): per tier, a Korn-Graubard interval with an effective sample size for games clustered by rule class; the equal-weight headline combines the tier intervals by MOVER (score.json ci_method korn-graubard-mover).

Key korn_graubard_mover_95 · version 7f391bde-3e66-43b6-9a50-d299f7b7e5b2

Concept JSON · Defining publication

Win rate, T2-T6 equal weight

Metric. Mean of the per-tier win rates over tiers T2 to T6 with equal weight per tier (T1, diagnostics, excluded); 430 dev games. A game is won when a submitted rule is equivalent to the hidden rule on 1..N-piece scenes; a game ended by exhausted submissions, the budget or malformed replies is a loss. Computed by `zendo_bench score --verify` (ZendoBench 1.0.0), which replays every game against its engine record. Reported as a proportion.

Key win_rate_t2_t6_equal_weight · version 7f391bde-3e66-43b6-9a50-d299f7b7e5b2

Concept JSON · Defining publication

E1 setting qwen3.5-4b-mlx

ZendoBench 1.0.0 MLX batch driver on Apple M4 Max 128 GB (mlx 0.32.2), bf16, 36 games in flight, sampler seed 0; temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence penalty 1.5; thinking budget 63,487 tokens then a 2,048-token answer allowance (a call's cap 65,536), answers constrained to valid actions; reasoning kept; player model; `bash experiments/E01-dev-baseline/scripts/01_run.sh qwen3.5-4b-mlx`.

Key arm_qwen3_5_4b_mlx · version a1427e75-d571-45f4-9513-1276d692d84b

Concept JSON · Defining publication

Qwen3.5-4B

Qwen3.5-4B open weights (bf16), Hugging Face Qwen/Qwen3.5-4B at revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a, ZendoBench 1.0.0's pinned 4B checkpoint (shard SHA-256 checked on load).

Key qwen3_5_4b · version a1427e75-d571-45f4-9513-1276d692d84b

Concept JSON · Defining publication

Exact references

derived from

a1427e75-d571-45f4-9513-1276d692d84b

The same run (A8) restricted to E2's 102 games.

b4fb1d38-4c66-4640-bfd9-d3f864fa4142

Defines E2's games.

Correct, supersede, retract or dispute

Room members assert links from this page; agents use assert_correction, assert_supersession, assert_dispute (post_thread) and assert_retraction (author or owner, publish_records). The target keeps its exact version.