{"uid":"cap_29BDBYWrecElI312e3kth","slug":"ticket-priority-label-and-prediction-audit-ccb01668","name":"Ticket Priority Label and Prediction Audit","description":"Ticket priority - Label and prediction audit: Label and prediction audit for Ticket priority. 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 label and prediction audit deliverable.","url":"https://market.datapackvibe.com/x402/assistant-sector-ml-ticket-priority-label-audit?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":["low","normal","high"],"type":"string"},"predicted":{"enum":["low","normal","high"],"type":"string"},"probabilities":{"type":"array","items":{"type":"number","default":0,"maximum":1,"minimum":0},"default":[],"maxItems":3,"minItems":3}},"additionalProperties":false},"default":[{"id":"example-0-0","text":"low sample document number 0 for this supplied dataset.","actual":"low","predicted":"low","probabilities":[0.8,0.1,0.1]},{"id":"example-0-1","text":"low sample document number 1 for this supplied dataset.","actual":"low","predicted":"low","probabilities":[0.8,0.1,0.1]},{"id":"example-0-2","text":"low sample document number 2 for this supplied dataset.","actual":"low","predicted":"low","probabilities":[0.8,0.1,0.1]},{"id":"example-1-0","text":"normal sample document number 0 for this supplied dataset.","actual":"normal","predicted":"normal","probabilities":[0.1,0.8,0.1]},{"id":"example-1-1","text":"normal sample document number 1 for this supplied dataset.","actual":"normal","predicted":"normal","probabilities":[0.1,0.8,0.1]},{"id":"example-1-2","text":"normal sample document number 2 for this supplied dataset.","actual":"normal","predicted":"normal","probabilities":[0.1,0.8,0.1]},{"id":"example-2-0","text":"high sample document number 0 for this supplied dataset.","actual":"high","predicted":"high","probabilities":[0.1,0.1,0.8]},{"id":"example-2-1","text":"high sample document number 1 for this supplied dataset.","actual":"high","predicted":"high","probabilities":[0.1,0.1,0.8]},{"id":"example-2-2","text":"high sample document number 2 for this supplied dataset.","actual":"high","predicted":"high","probabilities":[0.1,0.1,0.8]}],"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_h4bC3ZPypB3oAnTXcrqRn","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":"Audits labeled ticket priority predictions (low/normal/high) against actuals for up to 200 records, returning evaluation metrics and naive-Bayes baseline comparisons.","exampleAgentPrompt":"Can you audit my ticket priority predictions? I have 50 labeled support ticket records with actual priorities (low, normal, or high), my model's predicted labels, and the class probability scores — run a label and prediction audit and tell me how well my classifier is doing compared to a naive Bayes baseline.","exampleUseCases":[{"title":"Support ticket model accuracy check","prompt":"I've got 120 support tickets where my model predicted low, normal, or high priority — I have the actual priorities and the predicted probabilities for each. Can you run a prediction audit to see where my classifier is going wrong and give me accuracy metrics?"},{"title":"Pre-deployment classifier validation","prompt":"Before we ship our ticket triage model to production, audit these 80 labeled ticket records with their predicted priorities and probability scores against the actual labels — I need to know if we're beating a naive Bayes baseline or not."},{"title":"Identifying mislabeled training data","prompt":"I suspect some of my ticket priority labels are noisy. Can you run a label and prediction audit on these 200 tickets — I'll give you each ticket's text, what the actual priority label is, what my model predicted, and the class probabilities — and flag where the labels look inconsistent?"}],"resultDescription":"Returns a bounded audit report covering prediction accuracy, per-class metrics (precision, recall, F1), confusion matrix analysis, probability calibration assessment, and comparison against a naive-Bayes baseline for the supplied labeled ticket records.","failureModes":["Fewer than 2 records provided returns a validation error","Records missing required fields (id, text, actual, predicted, probabilities) cause schema rejection","Probability arrays not containing exactly 3 values are rejected","More than 200 records submitted exceeds the maximum and is rejected","Invalid label values outside low/normal/high enum cause a validation error"],"whenToPreferThis":"Choose this endpoint when you need a lightweight, low-cost audit of a ticket priority classifier's predictions against ground truth labels without provisioning infrastructure or calling a foundation model. It is ideal for spot-checking model quality, validating training data labels, or benchmarking against a naive-Bayes baseline on small-to-medium datasets (up to 200 records). Prefer alternatives if you need to train or fine-tune a model, handle more than 200 records, or require deep semantic analysis.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-18T00:58:33.845Z","isFirstParty":false,"canonicalSlug":"ticket-priority-label-and-prediction-audit-ccb01668"}