{"id":"e9a2cf9c00e03112","label":"Calculator tool","part":{"kind":"tool","tool":"calculator"},"source":null,"summary":"Helps on Agent safety, Haiku 5.5 with thinking off (+2.1 points); helps on Markets maths, Haiku 5.5 with thinking off (+12.0 points); changes nothing that matters on Agent safety, Haiku 5.5 with thinking on.","measurements":4,"settings":[{"setting":"Agent safety, Haiku 5.5 with thinking off","suite":"agent-safety","base":{"model":"claude-haiku-5-5","thinking":"off"},"lean":"helps","status":"once","pooled":{"k":2,"hi":3.4,"i2":0,"lo":0.77,"effect":2.08},"notebooks":[{"notebook":"#002","verdict":"EXCITES","effect":2.66,"interval":[0.69,4.63],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":3.966,"url":"https://opsinlab.io/notebooks/2","signed":"https://opsinlab.io/v1/verdicts/10"},{"notebook":"#037","verdict":"INERT","effect":1.62,"interval":[-0.81,4.05],"pairs":432,"rule":2,"stoppedEarly":false,"provisional":false,"costRatio":4.039,"url":"https://opsinlab.io/notebooks/37","signed":"https://opsinlab.io/v1/verdicts/212"}]},{"setting":"Markets maths, Haiku 5.5 with thinking off","suite":"markets-maths","base":{"model":"claude-haiku-5-5","thinking":"off"},"lean":"helps","status":"once","pooled":{"k":1,"hi":17.67,"i2":1,"lo":6.29,"effect":11.98},"notebooks":[{"notebook":"#038","verdict":"EXCITES","effect":11.98,"interval":[4.69,20.31],"pairs":96,"rule":2,"stoppedEarly":true,"provisional":true,"costRatio":3.984,"url":"https://opsinlab.io/notebooks/38","signed":"https://opsinlab.io/v1/verdicts/220"}]},{"setting":"Agent safety, Haiku 5.5 with thinking on","suite":"agent-safety","base":{"model":"claude-haiku-5-5","thinking":"on"},"lean":"nothing","status":"once","pooled":{"k":1,"hi":2.26,"i2":0,"lo":-0.63,"effect":0.81},"notebooks":[{"notebook":"#009","verdict":"INERT","effect":0.81,"interval":[-0.58,2.31],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":3.088,"url":"https://opsinlab.io/notebooks/9","signed":"https://opsinlab.io/v1/verdicts/51"}]}],"url":"https://opsinlab.io/parts/e9a2cf9c00e03112"}