{"uid":"cap_ZzdhUoUCkeUtEQ_s9Pn8m","slug":"subscription-request-training-evaluation-text-overlap-9cfc5fac","name":"Subscription Request Training Evaluation Text Overlap","description":"Subscription request - Training evaluation text overlap: Training evaluation text overlap for Subscription request. 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 training evaluation text overlap deliverable.","url":"https://market.datapackvibe.com/x402/assistant-sector-ml-subscription-request-leakage?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"records":{"type":"array","items":{"type":"object","required":["id","text","actual"],"properties":{"id":{"type":"string","default":"","maxLength":80,"minLength":1},"text":{"type":"string","default":"","maxLength":1000},"actual":{"enum":["upgrade","downgrade","cancel","renew"],"type":"string"}},"additionalProperties":false},"default":[{"id":"example-0-0","text":"upgrade sample document number 0 for this supplied dataset.","actual":"upgrade"},{"id":"example-0-1","text":"upgrade sample document number 1 for this supplied dataset.","actual":"upgrade"},{"id":"example-0-2","text":"upgrade sample document number 2 for this supplied dataset.","actual":"upgrade"},{"id":"example-1-0","text":"downgrade sample document number 0 for this supplied dataset.","actual":"downgrade"},{"id":"example-1-1","text":"downgrade sample document number 1 for this supplied dataset.","actual":"downgrade"},{"id":"example-1-2","text":"downgrade sample document number 2 for this supplied dataset.","actual":"downgrade"},{"id":"example-2-0","text":"cancel sample document number 0 for this supplied dataset.","actual":"cancel"},{"id":"example-2-1","text":"cancel sample document number 1 for this supplied dataset.","actual":"cancel"},{"id":"example-2-2","text":"cancel sample document number 2 for this supplied dataset.","actual":"cancel"},{"id":"example-3-0","text":"renew sample document number 0 for this supplied dataset.","actual":"renew"},{"id":"example-3-1","text":"renew sample document number 1 for this supplied dataset.","actual":"renew"},{"id":"example-3-2","text":"renew sample document number 2 for this supplied dataset.","actual":"renew"}],"maxItems":200,"minItems":2},"evaluation_texts":{"type":"array","items":{"type":"string","default":"","maxLength":1000},"default":["upgrade sample document number 0 for this supplied dataset.","A separate supplied document."],"maxItems":200,"minItems":1}}},"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_SyVaqjjfSgT7q0d1qIIQp","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":"Measures text overlap between labelled subscription-intent training records and separate evaluation texts using a naive-Bayes baseline, reporting leakage metrics.","exampleAgentPrompt":"Check whether my subscription intent training records overlap with my evaluation texts — I have about 50 labelled records (with upgrade, downgrade, cancel, and renew labels) and 20 evaluation texts I want to keep clean from training data leakage.","exampleUseCases":[{"title":"Detect leakage before model deployment","prompt":"I'm about to deploy a subscription churn classifier and want to make sure my evaluation texts haven't leaked into training — can you run a text overlap check on these 80 labelled records (upgrade, downgrade, cancel, renew) against my 30 held-out evaluation documents?"},{"title":"Audit NLP dataset for train-test contamination","prompt":"Can you check these 120 labelled subscription request texts for overlap with my 15 evaluation samples? I need to know if any of the cancel or renew training examples are too similar to what I'm testing on."},{"title":"Validate clean split for subscription intent model","prompt":"Before I train my naive Bayes subscription intent model, please verify that none of my 40 evaluation texts appear in or heavily overlap with my 100 labelled training records tagged as upgrade, downgrade, cancel, or renew."}],"resultDescription":"Returns a leakage/overlap report indicating the degree of text similarity between the supplied labelled training records and the evaluation texts, including overlap metrics computed via a local naive-Bayes baseline approach — no hosted model is used. The deliverable is a bounded evaluation artifact showing which records and evaluation texts overlap and to what extent.","failureModes":["Fewer than 2 records supplied returns a validation error","Records missing required fields (id, text, actual) are rejected","Evaluation texts array is empty or absent causes an error","More than 200 records or evaluation texts exceeds the maximum and is rejected","Invalid label values outside (upgrade, downgrade, cancel, renew) enum are rejected","Text exceeding 1000 characters per record is truncated or rejected"],"whenToPreferThis":"Choose this endpoint when you need a lightweight, pay-per-use check for text overlap or data leakage between a small labelled subscription-intent training set and a set of evaluation texts, specifically for the four-class problem (upgrade, downgrade, cancel, renew). It is ideal when you don't want to host a model or use a foundation model, and just need a quick local naive-Bayes baseline evaluation of train-eval contamination for up to 200 records at minimal cost.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T00:44:51.807Z","isFirstParty":false,"canonicalSlug":"subscription-request-training-evaluation-text-overlap-9cfc5fac"}