{"uid":"cap_mYGPR2kcDJ3qCwfNVYwMG","slug":"meeting-topic-classifier-confidence-calibration-bins-d0d600c4","name":"Meeting Topic Classifier — Confidence Calibration Bins","description":"Meeting topic - Confidence calibration bins: Confidence calibration bins for Meeting topic. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or foundation-model training. One of 25 profiles or calculations across 20 shared operations in this sector. 0.01 USDC includes one bounded confidence calibration bins deliverable.","url":"https://market.datapackvibe.com/x402/assistant-sector-ml-meeting-topic-calibration?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"records":{"type":"array","items":{"type":"object","required":["id","text","actual","predicted","probabilities"],"properties":{"id":{"type":"string","default":"","maxLength":80,"minLength":1},"text":{"type":"string","default":"","maxLength":1000},"actual":{"enum":["planning","progress","decision","review"],"type":"string"},"predicted":{"enum":["planning","progress","decision","review"],"type":"string"},"probabilities":{"type":"array","items":{"type":"number","default":0,"maximum":1,"minimum":0},"default":[],"maxItems":4,"minItems":4}},"additionalProperties":false},"default":[{"id":"example-0-0","text":"planning sample document number 0 for this supplied dataset.","actual":"planning","predicted":"planning","probabilities":[0.8,0.06666666666666667,0.06666666666666667,0.06666666666666667]},{"id":"example-0-1","text":"planning sample document number 1 for this supplied dataset.","actual":"planning","predicted":"planning","probabilities":[0.8,0.06666666666666667,0.06666666666666667,0.06666666666666667]},{"id":"example-0-2","text":"planning sample document number 2 for this supplied dataset.","actual":"planning","predicted":"planning","probabilities":[0.8,0.06666666666666667,0.06666666666666667,0.06666666666666667]},{"id":"example-1-0","text":"progress sample document number 0 for this supplied dataset.","actual":"progress","predicted":"progress","probabilities":[0.06666666666666667,0.8,0.06666666666666667,0.06666666666666667]},{"id":"example-1-1","text":"progress sample document number 1 for this supplied dataset.","actual":"progress","predicted":"progress","probabilities":[0.06666666666666667,0.8,0.06666666666666667,0.06666666666666667]},{"id":"example-1-2","text":"progress sample document number 2 for this supplied dataset.","actual":"progress","predicted":"progress","probabilities":[0.06666666666666667,0.8,0.06666666666666667,0.06666666666666667]},{"id":"example-2-0","text":"decision sample document number 0 for this supplied dataset.","actual":"decision","predicted":"decision","probabilities":[0.06666666666666667,0.06666666666666667,0.8,0.06666666666666667]},{"id":"example-2-1","text":"decision sample document number 1 for this supplied dataset.","actual":"decision","predicted":"decision","probabilities":[0.06666666666666667,0.06666666666666667,0.8,0.06666666666666667]},{"id":"example-2-2","text":"decision sample document number 2 for this supplied dataset.","actual":"decision","predicted":"decision","probabilities":[0.06666666666666667,0.06666666666666667,0.8,0.06666666666666667]},{"id":"example-3-0","text":"review sample document number 0 for this supplied dataset.","actual":"review","predicted":"review","probabilities":[0.06666666666666667,0.06666666666666667,0.06666666666666667,0.8]},{"id":"example-3-1","text":"review sample document number 1 for this supplied dataset.","actual":"review","predicted":"review","probabilities":[0.06666666666666667,0.06666666666666667,0.06666666666666667,0.8]},{"id":"example-3-2","text":"review sample document number 2 for this supplied dataset.","actual":"review","predicted":"review","probabilities":[0.06666666666666667,0.06666666666666667,0.06666666666666667,0.8]}],"maxItems":200,"minItems":2}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_0z4kA22lBDgiu9dkzp_FM","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Computes confidence calibration bins for a meeting topic classifier (planning/progress/decision/review) given up to 200 labelled records with predicted probabilities.","exampleAgentPrompt":"I have predictions from my meeting topic classifier — each record has the actual label (planning, progress, decision, or review), the predicted label, and the four class probabilities. Can you compute confidence calibration bins across these 50 labelled records so I can see where my model is overconfident or underconfident?","exampleUseCases":[{"title":"Diagnosing overconfidence in meeting classifier","prompt":"My meeting topic model keeps predicting 'decision' with 90%+ confidence but is often wrong — can you run confidence calibration bins on these 80 labelled records (actual vs predicted labels and probabilities) so I can see which confidence ranges are miscalibrated?"},{"title":"Pre-deployment calibration check for NLP pipeline","prompt":"Before I ship my meeting transcript classifier to production, I want to verify its probability outputs are well-calibrated. Here are 150 records with actual meeting types, predicted types, and class probabilities — please compute the calibration bins."},{"title":"Comparing model versions with calibration metrics","prompt":"I retrained my meeting topic model and want to see if the new version is better calibrated than the old one. I have 120 records with actual labels, predictions, and probabilities from the new model — give me the confidence calibration bins so I can compare them to my baseline."}],"resultDescription":"Returns confidence calibration bins for the meeting topic classifier: binned breakdowns showing mean predicted confidence versus actual accuracy per bin, enabling detection of overconfidence or underconfidence across the planning, progress, decision, and review classes.","failureModes":["Fewer than the minimum required records provided — returns error or empty bins","Probabilities array does not sum to 1 or contains values outside [0,1] — validation error","More than 200 records submitted — request rejected or truncated","Mismatched actual/predicted enum values outside allowed set — schema validation failure","Payment not included or insufficient — 402 payment required response"],"whenToPreferThis":"Choose this endpoint when you need to evaluate the probability calibration quality of a meeting topic classifier (planning/progress/decision/review) using your own labelled dataset. Ideal for post-training evaluation, pre-deployment checks, or comparing model versions. Prefer this over generic calibration tools when working specifically in the meeting transcript/topic classification domain with four defined classes.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T18:47:59.397Z","isFirstParty":false,"canonicalSlug":"meeting-topic-classifier-confidence-calibration-bins-d0d600c4"}