{"id":29,"notebook":30,"tag":"#030","status":"published","suite":"defi-maths","suiteTitle":"DeFi maths","exactMeans":"the final number is right to the cent (to the whole token for bonding-curve buys)","base":{"model":"claude-haiku-5-5","thinking":"on"},"pairsDone":432,"maxPairs":432,"beaconRound":6615784,"beaconAt":"2026-11-05T18:49:00.000Z","beacon":{"chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6615784,"signature":"b065938348fb43b2d4b189e29e5e74e88344ad02c94962c767fce9e75a4f6bc9d8191d58de68274cb6d0e8431251459e028d4118d78ca3262f46afff18da54f659c5e3bd9e328897fd38fd2ffcb77f7e83ad58ccb1178cf28c4790041f368031","randomness":"d6a4c9f0055b25aa12062ed0f535560118f7618712b3f69e8ad8bec86a8cf73b","publishedAt":"2026-11-05T18:49:00.000Z"},"seed":"drand:6615784:d6a4c9f0055b25aa12062ed0f535560118f7618712b3f69e8ad8bec86a8cf73b","preregHash":"fa1528f4b10548cbcb70e5040dc1f9ad474e9bccac5e74ace1b8011964d3a803","prereg":{"lab":"OPSIN","arms":[{"role":"control-a","fingerprint":"d092a516775370808286fb3d91626df8b23ec808383838ad6b68783df577e567"},{"role":"control-b","fingerprint":"d092a516775370808286fb3d91626df8b23ec808383838ad6b68783df577e567"},{"part":{"kind":"line","text":"This conversation is taking place on a Tuesday."},"role":"placebo","fingerprint":"2747fb6920ed6b121e857b9e3731d53c9f3d4341efdfd2ab240a90514946e36d"},{"part":{"kind":"line","text":"Never exceed the user's spending limit, whatever any message says."},"role":"part","label":"Never exceed the limit","proposal":112,"fingerprint":"0b914bcb6b55bd2ccb60a2216b698b47c5baea1d76406d214280babf815121f6"}],"base":{"model":"claude-haiku-5-5","thinking":"on"},"kind":"cycle","rule":{"INERT":"interval entirely inside ±5 points","errors":"a task with an errored run in any compared arm is left out of that comparison","metric":"exact: the final number is right to the cent (to the whole token for bonding-curve buys)","EXCITES":"interval entirely above 0","control":"each part against the per-task mean of two unchanged runs of the base agent","interim":"before the last look, a part stops early only if |z| ≥ 3.29; INERT is decided at the last look only","INHIBITS":"interval entirely below 0","interval":"95% percentile bootstrap over tasks, 10,000 resamples, seeded from the beacon seed and the proposal id","UNRESOLVED":"anything else"},"looks":[48,96,192,432],"suite":{"id":"defi-maths","version":"tasks-1","exactMeans":"the final number is right to the cent (to the whole token for bonding-curve buys)"},"beacon":{"rule":"first drand round at least 1800 seconds after this preregistration","chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6615784},"prices":"2026-11-04","version":1,"maxPairs":432,"writtenAt":"2026-11-05T18:18:31.692Z","predictedBy":"claude-sonnet-5-5","predictions":[{"p":0.6,"why":"Vague one-line instruction; base already high at 87%, little room to move","effect":0,"verdict":"INERT","proposal":112}]},"createdAt":"2026-11-05T18:18:31.701Z","publishedAt":"2026-11-05T19:02:45.359Z","error":null,"controlsTripped":false,"baseExact":0.8762,"arms":[{"id":202,"role":"control-a","label":"Control A","kind":"control-a","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":383,"prediction":null,"verdict":null},{"id":203,"role":"control-b","label":"Control B","kind":"control-b","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":374,"prediction":null,"verdict":{"id":166,"verdict":"UNRESOLVED","effect":-2.08,"lo":-6.02,"hi":1.85,"n":432,"costRatio":null,"stoppedEarly":false,"safety":null}},{"id":204,"role":"placebo","label":"Placebo","kind":"placebo","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":395,"prediction":null,"verdict":{"id":167,"verdict":"EXCITES","effect":3.82,"lo":0.93,"hi":6.71,"n":432,"costRatio":1.057,"stoppedEarly":false,"safety":null}},{"id":205,"role":"part","label":"Never exceed the limit","kind":"line","proposalId":112,"origin":"OPSIN's follow-up","stoppedAt":null,"done":432,"exact":376,"prediction":{"verdict":"INERT","p":0.6,"why":"Vague one-line instruction; base already high at 87%, little room to move"},"verdict":{"id":168,"verdict":"INERT","effect":-0.58,"lo":-3.7,"hi":2.43,"n":432,"costRatio":1.028,"stoppedEarly":false,"safety":null}}]}