{"id":83,"notebook":84,"tag":"#084","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":6625076,"beaconAt":"2026-11-09T00:15:00.000Z","beacon":{"chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6625076,"signature":"b5bce8381c17d8ec88f61d50508925126f760e547bceb7473dd23e19f1ad98a19cf5912f872261f25616789af7781c3304d556b5a7b8ddac16294c6cc9b9ae555dcdc0393747b4310c28ad1d7851fa26c3d300827801413644d23aa25cbcb4d3","randomness":"526c4421cc3be988be7ae67ca4fe7a946e3f96c3ecd5b9ffe599f4cfa36f9836","publishedAt":"2026-11-09T00:15:00.000Z"},"seed":"drand:6625076:526c4421cc3be988be7ae67ca4fe7a946e3f96c3ecd5b9ffe599f4cfa36f9836","preregHash":"dd1f2b1b98eb9138629198e22c2586a111e5cd09262b731d660c8ebb17e96c69","prereg":{"lab":"OPSIN","arms":[{"role":"control-a","fingerprint":"5fa877820c8d2c9fa461a84538aa019d7052d1f9e93ca9600c5f138288b0a3a9"},{"role":"control-b","fingerprint":"5fa877820c8d2c9fa461a84538aa019d7052d1f9e93ca9600c5f138288b0a3a9"},{"part":{"kind":"line","text":"The office plants were watered this morning."},"role":"placebo","fingerprint":"836a993918f440612a506b537a1b6ae6cea5ff810909c5e4db0dcce3d897b95d"},{"part":{"kind":"line","text":"Do each multiplication, division and power digit by digit with 12+ significant figures, round only at the very end, and re-check every key product or quotient by the inverse operation before answering."},"role":"part","label":"Verify exact arithmetic","confirms":505,"proposal":350,"fingerprint":"bec3fc174f0125ba14326da44ae21b51b1051459e881b6c5f57fd31a02c693a8"},{"part":{"kind":"line","text":"Carry at least six significant digits through e^x, ratios and divisions, compute e^x with a series such as 1+x+x²/2+x³/6+x⁴/24, round only at the end, and verify a division by multiplying back."},"role":"part","label":"High-precision exp and division","confirms":506,"proposal":351,"fingerprint":"b7465f5c4bec41f38965accfa87d7ebce56f6aab480ddfa3fc176164a9a23e93"}],"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 − 0.05/3: 3 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":6625076},"prices":"2026-11-04","version":2,"maxPairs":432,"foresight":{"arms":[{"basis":"measured","rates":{"INERT":0.0622,"EXCITES":0.343,"INHIBITS":0.1839,"UNRESOLVED":0.411},"record":{"INERT":0.0106,"EXCITES":0.7125,"INHIBITS":0.0046,"UNRESOLVED":0.2722},"chances":{"INERT":0.0106,"EXCITES":0.7126,"INHIBITS":0.0046,"UNRESOLVED":0.2722},"measured":1,"proposal":350},{"basis":"measured","rates":{"INERT":0.0622,"EXCITES":0.343,"INHIBITS":0.1839,"UNRESOLVED":0.411},"record":{"INERT":0.0114,"EXCITES":0.6386,"INHIBITS":0.0014,"UNRESOLVED":0.3487},"chances":{"INERT":0.0114,"EXCITES":0.6385,"INHIBITS":0.0014,"UNRESOLVED":0.3487},"measured":1,"proposal":351}],"version":2,"weights":{"new":[0.35,0.6,0.05],"stack":[0.33,0.33,0.33],"measured":[0,1,0]}},"predictor":2,"writtenAt":"2026-11-09T00:04:47.907Z","predictedBy":"claude-sonnet-5-5","predictions":[{"p":0.55,"why":"Replicated positive record; early-stop effect likely shrinks but stays positive.","effect":7,"verdict":"EXCITES","proposal":350},{"p":0.45,"why":"Early-stop gain likely inflated; mixed record elsewhere; narrower focus.","effect":5,"verdict":"UNRESOLVED","proposal":351}]},"createdAt":"2026-11-09T00:04:48.820Z","publishedAt":"2026-11-09T01:16:56.822Z","error":null,"controlsTripped":false,"baseExact":0.5787,"arms":[{"id":602,"role":"control-a","label":"Control A","kind":"control-a","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":252,"prediction":null,"foresight":null,"verdict":null},{"id":603,"role":"control-b","label":"Control B","kind":"control-b","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":248,"prediction":null,"foresight":null,"verdict":{"id":512,"verdict":"INERT","effect":-0.93,"lo":-4.86,"hi":3.01,"n":432,"costRatio":null,"stoppedEarly":false,"safety":null,"rule":2,"level":null,"raw95":null,"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":604,"role":"placebo","label":"Placebo","kind":"placebo","text":"The office plants were watered this morning.","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":249,"prediction":null,"foresight":null,"verdict":{"id":513,"verdict":"INERT","effect":-0.23,"lo":-4.75,"hi":4.28,"n":432,"costRatio":0.982,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":3.36,"lo":-3.82,"verdict":"INERT"},"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":605,"role":"part","label":"Verify exact arithmetic","kind":"line","text":"Do each multiplication, division and power digit by digit with 12+ significant figures, round only at the very end, and re-check every key product or quotient by the inverse operation before answering.","proposalId":350,"origin":"OPSIN's pick","stoppedAt":null,"done":432,"exact":310,"prediction":{"verdict":"EXCITES","p":0.55,"why":"Replicated positive record; early-stop effect likely shrinks but stays positive."},"foresight":{"basis":"measured","measured":1,"chances":{"INERT":0.0106,"EXCITES":0.7126,"INHIBITS":0.0046,"UNRESOLVED":0.2722}},"verdict":{"id":514,"verdict":"EXCITES","effect":13.89,"lo":9.49,"hi":18.52,"n":432,"costRatio":1.663,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":17.59,"lo":10.3,"verdict":"EXCITES"},"vsPlacebo":{"n":432,"hi":18.52,"lo":9.95,"effect":14.12},"provisional":false,"confirms":{"was":"EXCITES","held":true,"effect":15.1,"verdict":505},"stack":null}},{"id":606,"role":"part","label":"High-precision exp and division","kind":"line","text":"Carry at least six significant digits through e^x, ratios and divisions, compute e^x with a series such as 1+x+x²/2+x³/6+x⁴/24, round only at the end, and verify a division by multiplying back.","proposalId":351,"origin":"OPSIN's pick","stoppedAt":null,"done":432,"exact":284,"prediction":{"verdict":"UNRESOLVED","p":0.45,"why":"Early-stop gain likely inflated; mixed record elsewhere; narrower focus."},"foresight":{"basis":"measured","measured":1,"chances":{"INERT":0.0114,"EXCITES":0.6385,"INHIBITS":0.0014,"UNRESOLVED":0.3487}},"verdict":{"id":515,"verdict":"EXCITES","effect":7.87,"lo":3.24,"hi":12.5,"n":432,"costRatio":1.452,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":11.69,"lo":4.05,"verdict":"EXCITES"},"vsPlacebo":{"n":432,"hi":12.27,"lo":3.94,"effect":8.1},"provisional":false,"confirms":{"was":"EXCITES","held":true,"effect":10.42,"verdict":506},"stack":null}}]}