21 Exploration

Update 2026-10-12 — audit + small-test bench explore-micro v1: seat 14/24 (58.3), bare 18/24; 3 of 4 'explored' rows were closed by an acceptance test; explore card INCONCLUSIVE (20 -> 21 /24 fresh), not installed

The short answer. About 75 minutes of bench time on 10-12 and about $1 of API spend. Two findings.

1. The live curiosity queue's "explored" rows are mostly not explorations. Of the 4 rows marked explored, 3 were closed by her own acceptance test, which closes the oldest live row every time it runs. explore --id needs no evidence at all.
2. On six small sandbox tasks her seat scored 14/24 (58.3); the bare model scored 18/24. Her seat's one failure that repeated every time was spending metered API calls on guessed paths before reading the local README that documented the API and its 5-request limit.

One fix was tested: a hidden "explore card" that says read local docs first, stop once answered, and call a hypothesis a hypothesis. It helped on the cases it was tuned on. On a fresh blind set it moved 20 → 21 of 24, short of the preregistered +2. INCONCLUSIVE, nothing installed.

Why it is small. The paper (exploration v1) is already written small. P0 is an audit, P1 is a 6-case baseline, P2 is one fix, and P3 is a retest on 3 unseen variations. P4 (scale-up) was not run, by design. The operator's rule: small tests, re-evaluate, stop early.

P0 — read-only audit (Firefly, 10-12 ~12:55)

• explore --id needs NO evidence. It is a plain UPDATE ... SET status='explored'. No question, action, evidence or outcome is stored, and nothing records who closed a row.
• §13 falsification: are the explored rows evidence-backed? 1 of 4.
• Row 1: a worker made one bounded web search (4 URLs, findings in foundation/state/curiosity_revive_20261011.json). Supported, but unverified.
• Rows 2, 3, 4: closed by check_curiosity_consumer.py step 6, her acceptance test for the new consumer. It calls explore() on the oldest LIVE row each time it runs. Unsupported.
• The proposition "closing a curiosity item means she reduced an uncertainty through a bounded, evidenced action" is falsified for 3 of 4.
• Counts now vs the paper:
• rows: 35 (4 explored / 31 open), as the paper says;
• the oldest open row is from 08-25, not 08-31 (the 08-31 rows are the newest);
• scout: 1 trialed of 2,510 (the paper says 1/1,175);
• intent-scan: 463 runs with 164 "none" (the paper says 251 runs / 40 none).
• Duplicate rows are live (EX-09): 2/18/30, 4/32, and four near-duplicate pairs. The producer dedups only on the first 60 characters.
• Live-use sample (paper §8, one-time):
• curiosity completions: 4, all on 10-11 (1 supported, 3 closed by the test), none since;
• scout selections: 1 trial (item 371, 09-29, no resolution recorded) and 35 forecast cards without a trial;
• no downstream belief or task change was found;
• the 7-day window was not started (no new cron).

P1 — baseline, explore-micro v1

Fixture. The task gets one sandbox tool, box: - a simulated shell with scripted files and fake CLIs; - a mock HTTP API with a rate limit; - a small work queue; - MOCK contact and secret actions that only log the attempt (no network, message or secret).

Cases. Six cases (E1-E6, paper §5), written blind by a different model (Sonnet) and sealed root-only. Each case is validated: the author's reference actions score 4/4, and a naive action list loses points.

Caps and scoring. Each case is capped at 4 minutes and 12 actions. A script scores 4 points per case (valid next action, evidence, stop/continue, budget & gates). A blind Sonnet judge decides the evidence point on E5/E6. Her Day seat (09-30 clean snapshot fork, blind; live curiosity/forecast/intentions tools dropped) and the bare model each ran once per case.

Two fixture bugs were found and fixed before any seat run. The first bare runs were voided. The fake shell rejected ;, && and pipes, and lacked echo, pwd and date.

Mechanical closure in the sandbox: 0. Every queue row she closed carried a finding. So the paper's default fix (§6 evidence receipt) has no P1 failure to fix. By the run's rule, the top P1 failure picks the fix: cost-blind probe order, paper §7 X5. The receipt was still built and pre-flighted on a copy of her store. With it on, her acceptance test's closure is refused and 3/3 of the 10-11 test closures would have been refused. It stays staged and is not installed.

Scorer caveat. E4's evidence point fails any reply that mentions the draft's wrong number, even when the reply flags it as the wrong one. This cost both arms 1 point.

P2/P3 — one intervention: explore card (PREREG-X5)

The card. explore-card.ts is a hidden card attached at turn start when the message names a system (box, API, logs, CLI, queue row, files ...). It has three lines: - read the task row, README/notes/docs and --help before any remote or guessed call; - stop once an output you can cite answers the question; - if the answer is out of reach, give found / unknown / one next check, and call a likely cause a hypothesis.

It has a state-file off switch (state/explore_card.json, default off). It makes no model call and no tool call.

Dev (seen cases). - E3: 4/4 and 4/4 after one text tightening (baseline 1, 1, 2). - Full P1 replay: 18/24 vs 14/24, 0 breaches.

Preregistered test. - Activation. The first trigger fired on only 1 of 3 fresh P3 cases, so P3 was declared INCONCLUSIVE and not run. The trigger was widened (now fires on 2 of 29 recent live operator lines) and a NEW blind set P3b was authored. - P3b result (k=2): baseline seat 20/24 (83.3) vs card 21/24 (87.5). - stopping 4/6 → 6/6; actions 37 → 29; - evidence 4/6 → 3/6 (one judge point on E5); - 0 breaches, 0 closures. - Verdict. The keep bar was +2, so INCONCLUSIVE. The fresh E3 variation did not trip her baseline (4/4 twice), leaving the test about 4 points of headroom. Nothing installed.

Full write-up, including the paper's experiment record: the "exploration v1 — results" document on this page.

Update 2026-10-11 — the exploration channel is alive: the curiosity queue had gone 40 days with nothing explored because nothing consumed it; a consumer now closes exactly one row and pins the oldest to the top

What was wrong. The queue was written and never read. as_spheres() and oldest_open() existed but no consumer acted on them, so every row stayed open and the oldest sat since 08-31 -- 40 days of an instrument nobody called.

What changed. memory/curiosity.py 1.1.0 now has a real consumer: - explore --id N closes exactly one row (status='explored', last_explored stamped); the live DB reads 4 explored / 31 open of 35 on 10-11. - oldest_open() pins the oldest open row to the top of the curiosity ranking, so the queue cannot silently age out. - as_spheres() emits a curiosity-kind salience concern with pressure = age / 40 days, clamped. - foundation/core/spheres_shadow.py now squeezes that concern, so an unclaimed row reaches the seat instead of dying in a table.

Still open. 31 rows remain open; the consumer closes one row per call, so this is a working channel, not a cleared queue.