{"uid":"cap_ZFfC3PuO0ud4BisPjzSTf","slug":"confidence-calibration-report-b49da2bf","name":"Confidence Calibration Report","description":"Compute binary Brier score and count-weighted ECE for up to 256 declared held-out score/outcome pairs. Supports probability or percent scores, normalized to probabilities. Equal-width bins use exact rational boundaries: lower inclusive, upper exclusive, final bin includes 1. Empty bins report null means/gaps. No clinical validity claim.","url":"https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report?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","pairs","scoreUnits","binCount","evaluationSplit"],"properties":{"pairs":{"type":"array","maxItems":256,"minItems":1},"binCount":{"type":"integer","maximum":20,"minimum":2},"dataClass":{"enum":["public","synthetic"],"type":"string"},"scoreUnits":{"enum":["probability","percent"],"type":"string"},"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":["confidence-calibration-report"],"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":["47000"],"type":"string"}},"additionalProperties":false}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.047","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":"$0.047/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.047","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.047","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_pWVOQuddXCsrlOh9RFWjc","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.047","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Computes binary Brier score and count-weighted Expected Calibration Error (ECE) for up to 256 score/outcome pairs using equal-width probability bins","exampleAgentPrompt":"Can you compute a calibration report for my held-out predictions? I have 150 probability score/outcome pairs — scores are in probability units — and I want 10 equal-width bins. Please treat the data as synthetic.","exampleUseCases":[{"title":"Forecasting model calibration check","prompt":"I have 200 held-out prediction pairs from my binary forecasting model — each with a probability score and a 0/1 outcome. Can you run a calibration report with 10 bins to see my Brier score and ECE? The scores are in probability format and data is synthetic."},{"title":"Classifier confidence audit","prompt":"My classifier outputs confidence scores between 0 and 1 for a binary event. I've got 80 held-out public test cases and want to know how well-calibrated those scores are — please use 8 bins and compute the Brier score and ECE for me."},{"title":"Percent-scale prediction evaluation","prompt":"I have a set of 120 forecasts expressed as percentages (0–100) with their actual binary outcomes. Can you calibrate them using 5 equal-width bins and tell me the Brier score and expected calibration error? Mark the data as synthetic."}],"resultDescription":"Returns a structured calibration report including the Brier score, count-weighted ECE, per-bin statistics (mean predicted score, mean outcome, count, gap), exact rational bin boundaries, an input digest, and a receipt digest for auditability. Empty bins report null for mean and gap values.","failureModes":["Fewer than 1 or more than 256 pairs provided — request rejected","binCount outside 2–20 range — validation error","scoreUnits not matching actual score range (e.g. percent scores submitted as probability) — distorted results","evaluationSplit value other than declared-held-out-offline — schema error","Payment not included or insufficient — x402 payment required response","Malformed pair entries (missing score or outcome) — parsing error"],"whenToPreferThis":"Choose this endpoint when you need a fast, auditable, deterministic computation of Brier score and ECE over a small-to-medium held-out binary prediction dataset (up to 256 pairs). It is ideal for model evaluation pipelines, forecasting audits, or calibration checks where exact rational bin boundaries, reproducibility via input/receipt digests, and no external data dependencies matter. Prefer it over manual computation when you want structured bin-level diagnostics and auditability built in.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T07:03:15.218Z","isFirstParty":false,"canonicalSlug":"confidence-calibration-report-b49da2bf"}