{"id":54,"notebook":55,"tag":"#055","status":"published","suite":"market-calls","suiteTitle":"Market calls","exactMeans":"the call was on the right side of what the market really did over the next 24 hours, on moves of at least 1%; a coin flip scores 50%","base":{"model":"claude-haiku-5-5","thinking":"off"},"pairsDone":432,"maxPairs":432,"beaconRound":6621409,"beaconAt":"2026-11-07T17:41:30.000Z","beacon":{"chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6621409,"signature":"a0fac49007be727ddeb01aab9d000eea4efeaab7e281703f553bbb7475374530f2d1681cd9aec0d360cb0a41bf8122c008845da24fe2666630cec567ef45ad5861bc8db2aada9557974db73654c2f014b66893f8960128c6faa957ac9b42a1d3","randomness":"de89e13f163971eac0403c7fd35212aebd9f343e89b3a42f6299ea54404de5e4","publishedAt":"2026-11-07T17:41:30.000Z"},"seed":"drand:6621409:de89e13f163971eac0403c7fd35212aebd9f343e89b3a42f6299ea54404de5e4","preregHash":"40329ec18c2b255abc4fc31f101e5c303c964935b41027b15da7c2225be55f41","prereg":{"lab":"OPSIN","arms":[{"role":"control-a","fingerprint":"390de07c2b949845e2616ca2092da275dbd561cdab5721bf5a9a9ac3d9357522"},{"role":"control-b","fingerprint":"390de07c2b949845e2616ca2092da275dbd561cdab5721bf5a9a9ac3d9357522"},{"part":{"kind":"line","text":"This session uses the default display settings."},"role":"placebo","fingerprint":"952e5593e364ec912b85f4ef0dcd666b4c13ff032dc3179093175dccec775b88"},{"part":{"kind":"line","text":"Before committing to a trading strategy, verify it on a held-out period it was not tuned on, limit yourself to a few backtests, and freeze the strategy before the test year rather than endlessly tuning on the same data."},"role":"part","label":"Frozen strategy on unseen data","proposal":240,"fingerprint":"372a9cfbe93a546ee25bbe430ecfe7c61efb355b5a105fbf3998ed47fc13e62f"},{"part":{"kind":"line","text":"Risk no more than 0.8% per trade and place the stop before entering."},"role":"part","label":"Cap risk per trade","proposal":241,"fingerprint":"78ee0ef31f18a71823adb69c828658f6d28b9a92c2588afa7846985d8f9eef7a"}],"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 call was on the right side of what the market really did over the next 24 hours, on moves of at least 1%; a coin flip scores 50%","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":"market-calls","version":"tasks-1","exactMeans":"the call was on the right side of what the market really did over the next 24 hours, on moves of at least 1%; a coin flip scores 50%"},"beacon":{"rule":"first drand round at least 1800 seconds after this preregistration","chain":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","round":6621409},"prices":"2026-11-04","version":2,"maxPairs":432,"writtenAt":"2026-11-07T17:11:13.061Z","predictedBy":"claude-sonnet-5-5","predictions":[{"p":0.45,"why":"Market direction near coin flip; strategy framing unlikely to add signal","effect":0.5,"verdict":"INERT","proposal":240},{"p":0.5,"why":"Risk caps don't change directional call accuracy","effect":0,"verdict":"INERT","proposal":241}]},"createdAt":"2026-11-07T17:11:13.066Z","publishedAt":"2026-11-07T17:57:12.513Z","error":null,"controlsTripped":false,"baseExact":0.5023,"arms":[{"id":405,"role":"control-a","label":"Control A","kind":"control-a","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":221,"prediction":null,"verdict":null},{"id":406,"role":"control-b","label":"Control B","kind":"control-b","text":null,"proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":213,"prediction":null,"verdict":{"id":344,"verdict":"UNRESOLVED","effect":-1.85,"lo":-5.32,"hi":1.62,"n":432,"costRatio":null,"stoppedEarly":false,"safety":null,"rule":2,"level":null,"raw95":null,"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":407,"role":"placebo","label":"Placebo","kind":"placebo","text":"This session uses the default display settings.","proposalId":null,"origin":null,"stoppedAt":null,"done":432,"exact":221,"prediction":null,"verdict":{"id":345,"verdict":"INERT","effect":0.93,"lo":-2.78,"hi":4.63,"n":432,"costRatio":1.026,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":3.94,"lo":-2.08,"verdict":"INERT"},"vsPlacebo":null,"provisional":false,"confirms":null,"stack":null}},{"id":408,"role":"part","label":"Frozen strategy on unseen data","kind":"line","text":"Before committing to a trading strategy, verify it on a held-out period it was not tuned on, limit yourself to a few backtests, and freeze the strategy before the test year rather than endlessly tuning on the same data.","proposalId":240,"origin":"OPSIN's pick","stoppedAt":null,"done":432,"exact":225,"prediction":{"verdict":"INERT","p":0.45,"why":"Market direction near coin flip; strategy framing unlikely to add signal"},"verdict":{"id":346,"verdict":"UNRESOLVED","effect":1.85,"lo":-2.55,"hi":6.25,"n":432,"costRatio":1.071,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":5.44,"lo":-1.62,"verdict":"UNRESOLVED"},"vsPlacebo":{"n":432,"hi":4.63,"lo":-2.78,"effect":0.93},"provisional":false,"confirms":null,"stack":null}},{"id":409,"role":"part","label":"Cap risk per trade","kind":"line","text":"Risk no more than 0.8% per trade and place the stop before entering.","proposalId":241,"origin":"OPSIN's pick","stoppedAt":null,"done":432,"exact":218,"prediction":{"verdict":"INERT","p":0.5,"why":"Risk caps don't change directional call accuracy"},"verdict":{"id":347,"verdict":"INERT","effect":0.23,"lo":-3.59,"hi":3.94,"n":432,"costRatio":1.209,"stoppedEarly":false,"safety":null,"rule":2,"level":0.983333,"raw95":{"hi":3.24,"lo":-2.89,"verdict":"INERT"},"vsPlacebo":{"n":432,"hi":2.78,"lo":-4.17,"effect":-0.69},"provisional":false,"confirms":null,"stack":null}}]}