{"uid":"cap_6pZky-U1ziHNuew2UfuiY","slug":"delx-commerce-reliability-curve-calibration-52d15db8","name":"Delx Commerce — Reliability Curve (Calibration)","description":"Pay-per-result APIs for agents. No signup. Exact price. Verifiable delivery. USDC on Base + Solana via x402.","url":"https://commerce.delx.ai/api/v1/x402/reliability-curve?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"bins":{"type":"integer","description":"Number of calibration bins"},"outcomes":{"type":"array","description":"Binary outcomes 0/1 aligned with forecasts"},"forecasts":{"type":"array","description":"Forecast probabilities in [0,1]"}}},"responseSchema":{"type":"json","example":{"points":[{"n":2,"bin":0,"hit_rate":0,"mean_forecast":0.15},{"n":2,"bin":3,"hit_rate":1,"mean_forecast":0.8500000000000001}],"schema":"delx/util-reliability-curve/v1"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_2xNHhSeYsOB_gq28-BvbI","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Computes a reliability curve (calibration curve) from forecast probabilities and binary outcomes, grouped into bins, to evaluate forecast calibration quality.","exampleAgentPrompt":"I have 100 binary outcomes and their associated forecast probabilities — can you compute a reliability curve using 10 calibration bins so I can see how well my model's predictions line up with actual hit rates?","exampleUseCases":[{"title":"Model calibration audit for ML pipeline","prompt":"I trained a binary classifier and have 200 predictions alongside their actual 0/1 outcomes. Can you run a reliability curve with 5 bins so I can see whether my model is over- or under-confident?"},{"title":"Weather forecast calibration check","prompt":"I have daily rain forecasts as probabilities and the actual observed outcomes over 90 days. Please compute a reliability curve with 10 bins so I can evaluate how calibrated those forecasts really are."},{"title":"Sports prediction accuracy evaluation","prompt":"Here are 50 win-probability forecasts and the actual game results. Run a reliability curve with 8 bins so I can see if our forecasting model is trustworthy or systematically off."}],"resultDescription":"Returns a JSON array of calibration curve points, each containing the bin index, number of samples in the bin (n), the mean forecast probability for that bin, and the observed hit rate. The schema identifier is 'delx/util-reliability-curve/v1'.","failureModes":["Mismatched array lengths between forecasts and outcomes returns an error","Forecast values outside [0,1] may cause unexpected binning behavior","Too few data points relative to bin count yields bins with n=0 or n=1, producing noisy estimates","Invalid bins value (non-integer or <=0) causes a request error","Empty outcomes or forecasts arrays return no points"],"whenToPreferThis":"Choose this endpoint when you need a lightweight, pay-per-call reliability/calibration curve computation with no signup overhead. It is ideal for agents that periodically audit model calibration, need verifiable pay-per-result pricing via USDC/x402, or lack access to a statistical computing environment. Prefer it over building calibration code in-house when integrating into automated ML evaluation pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T04:56:43.289Z","isFirstParty":false,"canonicalSlug":"delx-commerce-reliability-curve-calibration-52d15db8"}