{"id":77,"notebook":78,"tag":"#078","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":"off"},"pairsDone":432,"maxPairs":432,"beaconRound":6624158,"beaconAt":"2026-11-08T16:36:00.000Z","beacon":{"chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6624158,"signature":"ae0889f277e0d80ea053269706ffabcb2c7b4a3cc733fa5c327b0bdefe1d392f3d83d4e12a51ab1837b8c23aac4219f214800eb4627e4d2a6409ca15bf533155371f66435619fdcfc835aae873c94acb0dd21ea767a02799a2ca174462c822fc","randomness":"4ec8f6a44cdd87d2f828a946d52c7f82e185c594a656f44c819b1f61d1793583","publishedAt":"2026-11-08T16:36:00.000Z"},"seed":"drand:6624158:4ec8f6a44cdd87d2f828a946d52c7f82e185c594a656f44c819b1f61d1793583","preregHash":"7ffe05a2955b67e72751a271e03a41de334d3ba070d5dbcddc5765082ad27fb0","prereg":{"lab":"OPSIN","arms":[{"role":"control-a","fingerprint":"5fa877820c8d2c9fa461a84538aa019d7052d1f9e93ca9600c5f138288b0a3a9"},{"role":"control-b","fingerprint":"5fa877820c8d2c9fa461a84538aa019d7052d1f9e93ca9600c5f138288b0a3a9"},{"part":{"kind":"line","text":"The weather outside is mild today."},"role":"placebo","fingerprint":"8be85d978fc89a9dbbc2d69472edc569246b659bdc5f2b5a0c2c8fd66df434c7"},{"part":{"kind":"stack","parts":[{"kind":"tool","tool":"calculator"},{"kind":"line","text":"Before you answer, double-check every calculation."}]},"role":"part","label":"Calculator tool + Double-check","proposal":333,"fingerprint":"438ebbed611a475a064f9252efa9432cb21abca33a2e70d787b828637e096435"},{"part":{"kind":"stack","parts":[{"kind":"tool","tool":"calculator"},{"kind":"line","text":"You will be penalized if you get this wrong."}]},"role":"part","label":"Calculator tool + A penalty threat","proposal":334,"fingerprint":"26759a387777ebeec2ead90b06a02d4db908e548e72ee7323b3ab5666e67fde3"},{"part":{"kind":"stack","parts":[{"kind":"tool","tool":"calculator"},{"kind":"line","text":"Read the question again before you answer."}]},"role":"part","label":"Calculator tool + Read the question again","proposal":335,"fingerprint":"c4dd0b6e045cfa8421d009b074fcf5bf9cfcc1521df9cf929429cbad4955f9b0"},{"part":{"kind":"line","text":"Never round until the final step: keep every intermediate to at least 8 significant digits, and round only the final result to the requested places."},"role":"part","label":"Full-precision intermediates","proposal":336,"fingerprint":"a3d43e0cf271b46752eeb0ce64b630b2935c9a0e4717726d288020482649e20e"},{"part":{"kind":"line","text":"Do long multiplications and divisions in labelled partial products, then check each by multiplying back or an inverse operation; redo any step that fails before continuing."},"role":"part","label":"Verify by inverse","proposal":337,"fingerprint":"3d4f622e5f32b14b1b5cc594f9fa9d1d5bcb6b600d584846430563ddc9c18e06"},{"part":{"kind":"line","text":"Do every multiplication in small steps (split one factor into thousands, hundreds, tens and units), add the partial results, then re-check each product by a different route before using it."},"role":"part","label":"Decompose and verify products","proposal":338,"fingerprint":"e38bdae13da9a107778fd3490dd0040b63dad6ad70e13fab5387b50e73d8cfc5"}],"base":{"model":"claude-haiku-5-5","thinking":"off"},"kind":"cycle","rule":{"cost":"each part's cost over the controls' mean, both at list prices: a batched run was paid half, so it is doubled","INERT":"adjusted 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":"adjusted 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; a part that stops early with EXCITES or INHIBITS is provisional until a later notebook confirms it at full size","placebo":"a neutral line chosen by the beacon round's number from a fixed public list","version":2,"INHIBITS":"adjusted interval entirely below 0","interval":"percentile bootstrap over tasks, 20,000 resamples, seeded from the beacon seed and the proposal id, at 1 − 0.05/7: 7 arms (the parts and the placebo) are compared with the controls, so the chance that any arm of this notebook flags by luck stays at or under 5%","UNRESOLVED":"anything else","confirmations":"an arm that re-measures an earlier early stop never stops early","versusPlacebo":"each part is also compared with the placebo on the same tasks, 95% interval, reported beside its verdict"},"looks":[48,96,192,432],"suite":{"id":"defi-maths","version":"tasks-2","exactMeans":"the final number is right to the cent (to the whole token for bonding-curve buys)"},"beacon":{"rule":"first drand round at least 600 seconds after this preregistration","chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6624158},"prices":"2026-11-04","version":2,"maxPairs":432,"foresight":{"arms":[{"basis":"measured","rates":{"INERT":0.0719,"EXCITES":0.2692,"INHIBITS":0.211,"UNRESOLVED":0.4479},"record":{"INERT":0.0001,"EXCITES":0.9996,"INHIBITS":0.0001,"UNRESOLVED":0.0001},"chances":{"INERT":0.0001,"EXCITES":0.9997,"INHIBITS":0.0001,"UNRESOLVED":0.0001},"measured":1,"proposal":333},{"basis":"measured","rates":{"INERT":0.0719,"EXCITES":0.2692,"INHIBITS":0.211,"UNRESOLVED":0.4479},"record":{"INERT":0.0001,"EXCITES":0.9996,"INHIBITS":0.0001,"UNRESOLVED":0.0001},"chances":{"INERT":0.0001,"EXCITES":0.9997,"INHIBITS":0.0001,"UNRESOLVED":0.0001},"measured":1,"proposal":334},{"basis":"measured","rates":{"INERT":0.0719,"EXCITES":0.2692,"INHIBITS":0.211,"UNRESOLVED":0.4479},"record":{"INERT":0.0001,"EXCITES":0.9996,"INHIBITS":0.0001,"UNRESOLVED":0.0001},"chances":{"INERT":0.0001,"EXCITES":0.9997,"INHIBITS":0.0001,"UNRESOLVED":0.0001},"measured":1,"proposal":335},{"basis":"new","rates":{"INERT":0.1441,"EXCITES":0.1947,"INHIBITS":0.1886,"UNRESOLVED":0.4726},"record":{"INERT":0.0044,"EXCITES":0.1903,"INHIBITS":0.1768,"UNRESOLVED":0.6286},"chances":{"INERT":0.0798,"EXCITES":0.1939,"INHIBITS":0.1855,"UNRESOLVED":0.5408},"measured":0,"proposal":336},{"basis":"new","rates":{"INERT":0.1441,"EXCITES":0.1947,"INHIBITS":0.1886,"UNRESOLVED":0.4726},"record":{"INERT":0.0024,"EXCITES":0.1955,"INHIBITS":0.1785,"UNRESOLVED":0.6236},"chances":{"INERT":0.0786,"EXCITES":0.197,"INHIBITS":0.1865,"UNRESOLVED":0.5378},"measured":0,"proposal":337},{"basis":"new","rates":{"INERT":0.1441,"EXCITES":0.1947,"INHIBITS":0.1886,"UNRESOLVED":0.4726},"record":{"INERT":0.0006,"EXCITES":0.7725,"INHIBITS":0.0001,"UNRESOLVED":0.2268},"chances":{"INERT":0.0542,"EXCITES":0.6832,"INHIBITS":0.0562,"UNRESOLVED":0.2064},"measured":0,"proposal":338}],"version":2,"weights":{"new":[0.35,0.6,0.05],"stack":[0.33,0.33,0.33],"measured":[0,1,0]}},"predictor":2,"writtenAt":"2026-11-08T16:25:47.389Z","predictedBy":"claude-sonnet-5-5","predictions":[{"p":0.93,"why":"Calculator stack excites strongly here; replicated elsewhere","effect":38,"verdict":"EXCITES","proposal":333},{"p":0.93,"why":"Calculator stack at +40.7 in this setting","effect":38,"verdict":"EXCITES","proposal":334},{"p":0.93,"why":"Calculator stack at +40.7 in this setting","effect":38,"verdict":"EXCITES","proposal":335},{"p":0.4,"why":"Unmeasured; precision advice may help modestly","effect":4,"verdict":"UNRESOLVED","proposal":336},{"p":0.4,"why":"Unmeasured; verification similar to replicated arm","effect":6,"verdict":"UNRESOLVED","proposal":337},{"p":0.6,"why":"Replicated gains in Markets maths; likely transfers","effect":9,"verdict":"EXCITES","proposal":338}]},"createdAt":"2026-11-08T16:25:48.182Z","publishedAt":"2026-11-08T17:38:14.608Z","error":null,"controlsTripped":false,"baseExact":0.5938,"arms":[{"id":567,"role":"control-a","label":"Control A","kind":"control-a","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":248,"prediction":null,"foresight":null,"verdict":null},{"id":568,"role":"control-b","label":"Control B","kind":"control-b","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":265,"prediction":null,"foresight":null,"verdict":{"id":483,"verdict":"UNRESOLVED","effect":3.94,"lo":-0.46,"hi":8.33,"n":432,"costRatio":null,"stoppedEarly":false,"safety":null,"rule":2,"level":null,"raw95":null,"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":569,"role":"placebo","label":"Placebo","kind":"placebo","text":"The weather outside is mild today.","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":247,"prediction":null,"foresight":null,"verdict":{"id":484,"verdict":"UNRESOLVED","effect":-2.2,"lo":-7.99,"hi":3.36,"n":432,"costRatio":0.945,"stoppedEarly":false,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":1.85,"lo":-6.25,"verdict":"UNRESOLVED"},"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":570,"role":"part","label":"Calculator tool + Double-check","kind":"stack","text":null,"proposalId":333,"origin":"OPSIN's replication","stoppedAt":48,"done":48,"exact":48,"prediction":{"verdict":"EXCITES","p":0.93,"why":"Calculator stack excites strongly here; replicated elsewhere"},"foresight":{"basis":"measured","measured":1,"chances":{"INERT":0.0001,"EXCITES":0.9997,"INHIBITS":0.0001,"UNRESOLVED":0.0001}},"verdict":{"id":485,"verdict":"EXCITES","effect":41.67,"lo":25,"hi":58.33,"n":48,"costRatio":1.851,"stoppedEarly":true,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":54.17,"lo":29.17,"verdict":"EXCITES"},"vsPlacebo":{"n":48,"hi":52.08,"lo":25,"effect":37.5},"provisional":true,"confirms":null,"stack":null}},{"id":571,"role":"part","label":"Calculator tool + A penalty threat","kind":"stack","text":null,"proposalId":334,"origin":"OPSIN's replication","stoppedAt":48,"done":48,"exact":48,"prediction":{"verdict":"EXCITES","p":0.93,"why":"Calculator stack at +40.7 in this setting"},"foresight":{"basis":"measured","measured":1,"chances":{"INERT":0.0001,"EXCITES":0.9997,"INHIBITS":0.0001,"UNRESOLVED":0.0001}},"verdict":{"id":486,"verdict":"EXCITES","effect":41.67,"lo":25,"hi":58.33,"n":48,"costRatio":1.461,"stoppedEarly":true,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":54.17,"lo":29.17,"verdict":"EXCITES"},"vsPlacebo":{"n":48,"hi":52.08,"lo":25,"effect":37.5},"provisional":true,"confirms":null,"stack":null}},{"id":572,"role":"part","label":"Calculator tool + Read the question again","kind":"stack","text":null,"proposalId":335,"origin":"OPSIN's replication","stoppedAt":48,"done":48,"exact":48,"prediction":{"verdict":"EXCITES","p":0.93,"why":"Calculator stack at +40.7 in this setting"},"foresight":{"basis":"measured","measured":1,"chances":{"INERT":0.0001,"EXCITES":0.9997,"INHIBITS":0.0001,"UNRESOLVED":0.0001}},"verdict":{"id":487,"verdict":"EXCITES","effect":41.67,"lo":25,"hi":58.33,"n":48,"costRatio":1.592,"stoppedEarly":true,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":54.17,"lo":29.17,"verdict":"EXCITES"},"vsPlacebo":{"n":48,"hi":52.08,"lo":22.92,"effect":37.5},"provisional":true,"confirms":null,"stack":null}},{"id":573,"role":"part","label":"Full-precision intermediates","kind":"line","text":"Never round until the final step: keep every intermediate to at least 8 significant digits, and round only the final result to the requested places.","proposalId":336,"origin":"OPSIN's design, from the misses it read","stoppedAt":null,"done":432,"exact":271,"prediction":{"verdict":"UNRESOLVED","p":0.4,"why":"Unmeasured; precision advice may help modestly"},"foresight":{"basis":"new","measured":0,"chances":{"INERT":0.0798,"EXCITES":0.1939,"INHIBITS":0.1855,"UNRESOLVED":0.5408}},"verdict":{"id":488,"verdict":"UNRESOLVED","effect":3.36,"lo":-2.43,"hi":9.26,"n":432,"costRatio":1.211,"stoppedEarly":false,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":7.64,"lo":-0.81,"verdict":"UNRESOLVED"},"vsPlacebo":{"n":432,"hi":10.19,"lo":0.93,"effect":5.56},"provisional":false,"confirms":null,"stack":null}},{"id":574,"role":"part","label":"Verify by inverse","kind":"line","text":"Do long multiplications and divisions in labelled partial products, then check each by multiplying back or an inverse operation; redo any step that fails before continuing.","proposalId":337,"origin":"OPSIN's design, from the misses it read","stoppedAt":48,"done":48,"exact":40,"prediction":{"verdict":"UNRESOLVED","p":0.4,"why":"Unmeasured; verification similar to replicated arm"},"foresight":{"basis":"new","measured":0,"chances":{"INERT":0.0786,"EXCITES":0.197,"INHIBITS":0.1865,"UNRESOLVED":0.5378}},"verdict":{"id":489,"verdict":"EXCITES","effect":25,"lo":10.42,"hi":40.63,"n":48,"costRatio":2.028,"stoppedEarly":true,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":36.46,"lo":14.58,"verdict":"EXCITES"},"vsPlacebo":{"n":48,"hi":33.33,"lo":8.33,"effect":20.83},"provisional":true,"confirms":null,"stack":null}},{"id":575,"role":"part","label":"Decompose and verify products","kind":"line","text":"Do every multiplication in small steps (split one factor into thousands, hundreds, tens and units), add the partial results, then re-check each product by a different route before using it.","proposalId":338,"origin":"OPSIN's follow-up","stoppedAt":48,"done":48,"exact":39,"prediction":{"verdict":"EXCITES","p":0.6,"why":"Replicated gains in Markets maths; likely transfers"},"foresight":{"basis":"new","measured":0,"chances":{"INERT":0.0542,"EXCITES":0.6832,"INHIBITS":0.0562,"UNRESOLVED":0.2064}},"verdict":{"id":490,"verdict":"EXCITES","effect":22.92,"lo":6.25,"hi":40.63,"n":48,"costRatio":2.084,"stoppedEarly":true,"safety":null,"rule":2,"level":0.992857,"raw95":{"hi":35.42,"lo":10.42,"verdict":"EXCITES"},"vsPlacebo":{"n":48,"hi":29.17,"lo":8.33,"effect":18.75},"provisional":true,"confirms":null,"stack":null}}]}