{"slug":"api-zfinia-com-x402-v1-dataset-overlap-audit-efafd3","title":"Check whether datasets that are meant to be disjoint share any keys","host":"api.zfinia.com","method":"POST","resource":"https://api.zfinia.com/x402/v1/dataset-overlap-audit","category":"code","description":"Check whether datasets that are meant to be disjoint share any keys. A key in both a training and an evaluation split means the evaluation is measuring memorisation, and every figure computed from it is optimistic. Reports overlap per pair with the share of the smaller set, since that is the one who","price_listed":0.16,"price_asked":null,"state":"no_terms","state_label":"Answers HTTP 429 without x402 payment terms","checks_7d":1,"answered_7d":0,"latency_ms_median":null,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"datasets":[{"csv":"customer_id,label\nC-001,1\nC-002,0\nC-003,1\nC-004,0\n","name":"train"},{"csv":"customer_id,label\nC-003,1\nC-005,0\n","name":"evaluation"},{"csv":"customer_id,label\nC-006,1\n","name":"holdout"}],"key":["customer_id"]},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"datasets":{"items":{"additionalProperties":false,"properties":{"csv":{"maxLength":262144,"type":"string"},"name":{"maxLength":64,"type":"string"}},"required":["name","csv"],"type":"object"},"maxItems":10,"minItems":2,"type":"array"},"delimiter":{"maxLength":1,"minLength":1,"type":"string"},"expect_disjoint":{"type":"boolean"},"key":{"items":{"maxLength":256,"type":"string"},"maxItems":4,"minItems":1,"type":"array"}},"required":["datasets","key"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-04","reachable":true,"status":429,"valid_402":false,"asked_usdc":null,"price_match":null,"latency_ms":269,"error":null}],"description_full":"Check whether datasets that are meant to be disjoint share any keys. A key in both a training and an evaluation split means the evaluation is measuring memorisation, and every figure computed from it is optimistic. Reports overlap per pair with the share of the smaller set, since that is the one whose measurements are compromised, plus keys appearing in every dataset.","last_updated":"2026-10-04T08:12:11.663Z","schemes":["exact"]}