{"uid":"cap_J22uv4bxr7-zC_L1aUeCS","slug":"knowledge-topic-classifier-supplied-group-evaluation-8a08bcb7","name":"Knowledge Topic Classifier – Supplied-Group Evaluation","description":"Knowledge topic - Supplied-group evaluation: Supplied-group evaluation for Knowledge 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 supplied-group evaluation deliverable.","url":"https://market.datapackvibe.com/x402/assistant-sector-ml-knowledge-topic-group-evaluation?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"records":{"type":"array","items":{"type":"object","required":["id","text","actual","predicted","group"],"properties":{"id":{"type":"string","default":"","maxLength":80,"minLength":1},"text":{"type":"string","default":"","maxLength":1000},"group":{"type":"string","default":"","maxLength":80},"actual":{"enum":["setup","usage","troubleshooting","reference"],"type":"string"},"predicted":{"enum":["setup","usage","troubleshooting","reference"],"type":"string"}},"additionalProperties":false},"default":[{"id":"example-0-0","text":"setup sample document number 0 for this supplied dataset.","group":"a","actual":"setup","predicted":"setup"},{"id":"example-0-1","text":"setup sample document number 1 for this supplied dataset.","group":"b","actual":"setup","predicted":"setup"},{"id":"example-0-2","text":"setup sample document number 2 for this supplied dataset.","group":"a","actual":"setup","predicted":"setup"},{"id":"example-1-0","text":"usage sample document number 0 for this supplied dataset.","group":"a","actual":"usage","predicted":"usage"},{"id":"example-1-1","text":"usage sample document number 1 for this supplied dataset.","group":"b","actual":"usage","predicted":"usage"},{"id":"example-1-2","text":"usage sample document number 2 for this supplied dataset.","group":"a","actual":"usage","predicted":"usage"},{"id":"example-2-0","text":"troubleshooting sample document number 0 for this supplied dataset.","group":"a","actual":"troubleshooting","predicted":"troubleshooting"},{"id":"example-2-1","text":"troubleshooting sample document number 1 for this supplied dataset.","group":"b","actual":"troubleshooting","predicted":"troubleshooting"},{"id":"example-2-2","text":"troubleshooting sample document number 2 for this supplied dataset.","group":"a","actual":"troubleshooting","predicted":"troubleshooting"},{"id":"example-3-0","text":"reference sample document number 0 for this supplied dataset.","group":"a","actual":"reference","predicted":"reference"},{"id":"example-3-1","text":"reference sample document number 1 for this supplied dataset.","group":"b","actual":"reference","predicted":"reference"},{"id":"example-3-2","text":"reference sample document number 2 for this supplied dataset.","group":"a","actual":"reference","predicted":"reference"}],"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_EALw0sod7keaj1lJGcYiu","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":"Evaluates a supplied set of up to 200 labelled text records for knowledge-topic classification (setup/usage/troubleshooting/reference), broken down by user-defined groups, using local naive-Bayes baselines.","exampleAgentPrompt":"Evaluate my knowledge-topic classifier predictions — I have 150 labelled records, each tagged with actual and predicted categories (setup, usage, troubleshooting, or reference) and split into groups 'A' and 'B'. Give me a breakdown of how well the predictions match actuals for each group.","exampleUseCases":[{"title":"Documentation classifier audit by team","prompt":"I've got 180 labelled support docs where each doc has a predicted and actual topic tag — either setup, usage, troubleshooting, or reference — and they're split between two teams, 'frontend' and 'backend'. Can you run a group evaluation so I can see which team's classifier predictions are more accurate?"},{"title":"A/B comparison of two labelling approaches","prompt":"I ran two different labelling pipelines on the same corpus of knowledge base articles — group 'pipeline_v1' and group 'pipeline_v2' — and I have the actual and predicted topic labels (setup, usage, troubleshooting, reference) for 120 records. Evaluate both groups so I can see which pipeline does better."},{"title":"Baseline check before model training","prompt":"Before I invest in training a full model, can you evaluate these 90 labelled knowledge-topic records split by product area ('core' and 'extensions') against a naive-Bayes baseline? I have actual labels and predicted labels in setup/usage/troubleshooting/reference format for each record."}],"resultDescription":"Returns a bounded evaluation deliverable containing per-group classification metrics (e.g. accuracy, per-class breakdown) for the supplied labelled records, along with a naive-Bayes baseline comparison. No hosted model is trained; results are computed locally from the provided actual and predicted labels across the defined groups.","failureModes":["More than 200 records submitted — exceeds the bounded evaluation limit","Records missing required fields (id, text, actual, predicted, group) — validation error","Labels outside the allowed enum (setup, usage, troubleshooting, reference) — rejected","Empty records array — no evaluation possible","Malformed JSON payload — request rejected","Payment not completed via x402 protocol — endpoint not executed"],"whenToPreferThis":"Choose this endpoint when you have a small, pre-labelled dataset of knowledge-topic documents (up to 200 records) segmented into user-defined groups, and you want a quick, cheap ($0.01 USDC) evaluation of classifier predictions against actuals with a naive-Bayes baseline — without needing to train or host any model. Prefer it over general ML evaluation platforms when your labels are in the specific setup/usage/troubleshooting/reference taxonomy and you want group-level breakdowns in a single API call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-18T00:58:31.194Z","isFirstParty":false,"canonicalSlug":"knowledge-topic-classifier-supplied-group-evaluation-8a08bcb7"}