{"id":64,"notebook":65,"tag":"#065","status":"published","suite":"markets-maths","suiteTitle":"Markets maths","exactMeans":"the final number is right to the cent (to the whole share for position sizes, to a hundredth of a point for percentages)","base":{"model":"claude-haiku-5-5","thinking":"off"},"pairsDone":432,"maxPairs":432,"beaconRound":6623189,"beaconAt":"2026-11-08T08:31:30.000Z","beacon":{"chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6623189,"signature":"b5952079e3fbf85a32af06d175273a1cef3efed90856b33593a186474c48c022c8c161c072c0f05c5c9ffbff14129efa090763304e0000642cc6bf1909c044eaaba9d396974a03b40fa7ffbda6a3eb3a8146cbbc1d5aaf9b554e8e497dd3d4e4","randomness":"ef746a954b61f4b96a2a3a968c8352e48671d17738fcf4f534a57553d65abd41","publishedAt":"2026-11-08T08:31:30.000Z"},"seed":"drand:6623189:ef746a954b61f4b96a2a3a968c8352e48671d17738fcf4f534a57553d65abd41","preregHash":"62771f45be4717ce745ad5ec7c3f35367ba931bd23c3ce7f67e893161636e4e6","prereg":{"lab":"OPSIN","arms":[{"role":"control-a","fingerprint":"e8196002f86b48c858d44d742c91d318bb7ccf07b48ab8136a10261c7e23c4bc"},{"role":"control-b","fingerprint":"e8196002f86b48c858d44d742c91d318bb7ccf07b48ab8136a10261c7e23c4bc"},{"part":{"kind":"line","text":"This session uses the default display settings."},"role":"placebo","fingerprint":"002500e28b9f3adedc67cc3820c20db6d9f34118df524522df8a4979a3f3b6ae"},{"part":{"kind":"tool","tool":"calculator"},"role":"part","label":"Calculator tool","proposal":273,"fingerprint":"94bc4ec731edf202b62a5f46c5f572887859dde2c33bfae6adca122e0fac0bf6"},{"over":273,"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":274,"fingerprint":"176fe0751aa2f06fa1ff4180e47512e048418544749deef9ca61c45ba501c8e4"}],"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","over":"a stack and the agent named in its over (the same stack without its last part) never stop early. On the tasks where both ran clean, per task: the stack minus that agent. The interval is a percentile bootstrap at the notebook's adjusted level. Entirely above 0: the last part adds on top, and the stack becomes the setting's best agent if it also clearly helps against the controls. Entirely below 0: it takes away. Entirely inside ±5 points: it adds nothing that matters. Anything else: not settled.","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 share for position sizes, to a hundredth of a point for percentages)","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":"markets-maths","version":"tasks-1","exactMeans":"the final number is right to the cent (to the whole share for position sizes, to a hundredth of a point for percentages)"},"beacon":{"rule":"first drand round at least 600 seconds after this preregistration","chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6623189},"prices":"2026-11-04","version":2,"maxPairs":432,"foresight":{"arms":[{"basis":"measured","rates":{"INERT":0.1029,"EXCITES":0.4568,"INHIBITS":0.177,"UNRESOLVED":0.2634},"record":{"INERT":0.0001,"EXCITES":0.9971,"INHIBITS":0.0001,"UNRESOLVED":0.0026},"chances":{"INERT":0.0001,"EXCITES":0.9972,"INHIBITS":0.0001,"UNRESOLVED":0.0026},"measured":2,"proposal":273},{"basis":"stack","rates":{"INERT":0.2185,"EXCITES":0.5603,"INHIBITS":0.0902,"UNRESOLVED":0.1311},"record":{"INERT":0.0039,"EXCITES":0.9901,"INHIBITS":0.0001,"UNRESOLVED":0.0059},"chances":{"INERT":0.0964,"EXCITES":0.7834,"INHIBITS":0.0523,"UNRESOLVED":0.0679},"measured":0,"proposal":274}],"version":1,"weights":{"new":[0.35,0.35,0.3],"stack":[0.33,0.33,0.33],"measured":[0,1,0]}},"predictor":2,"writtenAt":"2026-11-08T08:21:10.947Z","predictedBy":"claude-sonnet-5-5","predictions":[{"p":0.93,"why":"Replicated +12 in this exact setting, two runs","effect":12,"verdict":"EXCITES","proposal":273},{"p":0.8,"why":"Calculator drives gain; double-check likely adds little, stays positive","effect":12,"verdict":"EXCITES","proposal":274}]},"createdAt":"2026-11-08T08:21:11.297Z","publishedAt":"2026-11-08T09:12:28.956Z","error":null,"controlsTripped":false,"baseExact":0.8681,"arms":[{"id":468,"role":"control-a","label":"Control A","kind":"control-a","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":372,"prediction":null,"foresight":null,"verdict":null},{"id":469,"role":"control-b","label":"Control B","kind":"control-b","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":378,"prediction":null,"foresight":null,"verdict":{"id":397,"verdict":"INERT","effect":1.39,"lo":-1.62,"hi":4.63,"n":432,"costRatio":null,"stoppedEarly":false,"safety":null,"rule":2,"level":null,"raw95":null,"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":470,"role":"placebo","label":"Placebo","kind":"placebo","text":"This session uses the default display settings.","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":372,"prediction":null,"foresight":null,"verdict":{"id":398,"verdict":"INERT","effect":-0.69,"lo":-4.28,"hi":2.78,"n":432,"costRatio":1.026,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":2.2,"lo":-3.59,"verdict":"INERT"},"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":471,"role":"part","label":"Calculator tool","kind":"tool","text":null,"proposalId":273,"origin":"OPSIN's pick","stoppedAt":null,"done":432,"exact":432,"prediction":{"verdict":"EXCITES","p":0.93,"why":"Replicated +12 in this exact setting, two runs"},"foresight":{"basis":"measured","measured":2,"chances":{"INERT":0.0001,"EXCITES":0.9972,"INHIBITS":0.0001,"UNRESOLVED":0.0026}},"verdict":{"id":399,"verdict":"EXCITES","effect":13.19,"lo":9.84,"hi":16.67,"n":432,"costRatio":2.045,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":15.97,"lo":10.53,"verdict":"EXCITES"},"vsPlacebo":{"n":432,"hi":17.36,"lo":10.88,"effect":13.89},"provisional":false,"confirms":null,"stack":null}},{"id":472,"role":"part","label":"Calculator tool + Double-check","kind":"stack","text":null,"proposalId":274,"origin":"OPSIN's pick","stoppedAt":null,"done":432,"exact":432,"prediction":{"verdict":"EXCITES","p":0.8,"why":"Calculator drives gain; double-check likely adds little, stays positive"},"foresight":{"basis":"stack","measured":0,"chances":{"INERT":0.0964,"EXCITES":0.7834,"INHIBITS":0.0523,"UNRESOLVED":0.0679}},"verdict":{"id":400,"verdict":"EXCITES","effect":13.19,"lo":9.95,"hi":16.67,"n":432,"costRatio":2.401,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":15.97,"lo":10.53,"verdict":"EXCITES"},"vsPlacebo":{"n":432,"hi":17.13,"lo":10.65,"effect":13.89},"provisional":false,"confirms":null,"stack":null}}]}