{"uid":"cap_Q2xBJhSuQ5dvtYaNGlY7J","slug":"intention-threshold-sweep-c0eb2b0a","name":"Intention Threshold Sweep","description":"Replay up to 24 declared thresholds over at most 512 labelled scores in contiguous half-open trials. Reports rest rising-edge false events, rest active time, intention misses and first-active latency. State carries across trials; scores are held to the next sample. Held-out status is declared, not verified. No automatic selection or live control.","url":"https://www.mahastrategies.com/api/v1/micro/intention-threshold-sweep?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["dataClass","trials","thresholds","scoreUnits","evaluationSplit"],"properties":{"trials":{"type":"array","maxItems":16,"minItems":1},"dataClass":{"enum":["public","synthetic"],"type":"string"},"scoreUnits":{"enum":["unit-interval"],"type":"string"},"thresholds":{"type":"array","maxItems":24,"minItems":1},"evaluationSplit":{"enum":["declared-held-out-offline"],"type":"string"}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["version","offerId","amountBaseUnits","inputDigest","result","boundaries","receiptDigest"],"properties":{"result":{"type":"object"},"offerId":{"enum":["intention-threshold-sweep"],"type":"string"},"version":{"enum":["maha-microproducts/0.1"],"type":"string"},"boundaries":{"type":"array","maxItems":128,"minItems":0},"inputDigest":{"type":"string","maxLength":71},"receiptDigest":{"type":"string","maxLength":71},"amountBaseUnits":{"enum":["73000"],"type":"string"}},"additionalProperties":false}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.073","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.073/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.073","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.073","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_oyz-e6zDnLQYYV3cLEFOq","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.073","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Sweeps up to 24 declared classification thresholds across labelled score sequences, reporting false-positive events, active time, intention misses, and first-active latency across contiguous trials.","exampleAgentPrompt":"Sweep 5 thresholds — 0.3, 0.4, 0.5, 0.6, 0.7 — over my 3 synthetic trials with unit-interval scores and declared held-out offline split, then report false events, active time, intention misses, and first-active latency for each threshold.","exampleUseCases":[{"title":"Optimizing intention detector cutoff","prompt":"I have 8 trial sequences of unit-interval intention scores labeled as synthetic data. Can you sweep thresholds at 0.2, 0.35, 0.5, 0.65, and 0.8 using a declared held-out offline split and tell me which threshold gives the fewest intention misses and lowest false event rate?"},{"title":"Benchmarking first-active latency","prompt":"Run a threshold sweep over my 4 public-class trial score arrays with thresholds 0.4, 0.5, and 0.6, using unit-interval scores and declared held-out offline evaluation — I specifically need the first-active latency and rest active time figures for each threshold."},{"title":"Auditing false positives across decision boundaries","prompt":"I need to audit how many rising-edge false events my intention detection system generates at thresholds 0.25, 0.45, 0.55, 0.75, and 0.9 across 10 synthetic trial sequences with unit-interval scores — use the declared held-out offline split and report rest active time alongside the false event counts."}],"resultDescription":"Returns a structured result per threshold including rising-edge false event counts, rest active time, intention miss counts, and first-active latency, along with trial boundary markers, input digest, receipt digest, version, and offer ID for auditability.","failureModes":["Exceeds 24 threshold limit — request rejected","Exceeds 16 trial array limit — request rejected","Score values outside unit-interval [0,1] range — validation error","Invalid dataClass or evaluationSplit enum value — schema error","Malformed or missing required body fields — 400 error","Payment authorization failure — request not processed"],"whenToPreferThis":"Choose this endpoint when you need to evaluate multiple classification thresholds simultaneously over labelled, contiguous trial sequences with stateful carry-across, particularly for intention detection or signal-detection workloads. It is purpose-built for declared held-out offline evaluation rather than live or adaptive control, making it ideal for reproducible threshold benchmarking on synthetic or public data classes.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T06:55:09.916Z","isFirstParty":false,"canonicalSlug":"intention-threshold-sweep-c0eb2b0a"}