{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BR6WF6OLPS5D4QABJQZCSSMYKB","short_pith_number":"pith:BR6WF6OL","schema_version":"1.0","canonical_sha256":"0c7d62f9cb7cba3e40014c3229499850751082822fe93489973fd7cf9371e7fb","source":{"kind":"arxiv","id":"2507.17026","version":2},"attestation_state":"computed","paper":{"title":"Conformal C2ST: Turning weak classifiers into strong two-sample tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"James G. Scott, Tianyu Chen, Vansh Bansal","submitted_at":"2025-07-22T21:30:06Z","abstract_excerpt":"The two-sample testing problem, a fundamental task in statistics and machine learning, seeks to determine whether two sets of samples, drawn from underlying distributions $p$ and $q$, are in fact identically distributed (i.e. whether $p=q$). A popular and intuitive approach is the classifier two-sample test (C2ST), where a classifier is trained to distinguish between samples from $p$ and $q$. Yet despite simplicity of the C2ST, its reliability hinges on access to a near-Bayes-optimal classifier, a requirement that is rarely met and difficult to verify. This raises a major open question: can a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.17026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-22T21:30:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5000752731ac40cda85e6cf8bef58d6392b4368003b296611bc80afbf24e4a4c","abstract_canon_sha256":"b3fa99c32470737a8cc700c7323922efe695b224b958e233ca242f1ae65f34dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:25.005231Z","signature_b64":"4Lc62ytFUaV2803IjlExwR1a63zTHS3cqnCG4lf3Fg2vYTq/t2c07tgK5jwgk3U6wOPy46t8/OsAfNV4zif2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c7d62f9cb7cba3e40014c3229499850751082822fe93489973fd7cf9371e7fb","last_reissued_at":"2026-06-01T02:03:25.004293Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:25.004293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conformal C2ST: Turning weak classifiers into strong two-sample tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"James G. Scott, Tianyu Chen, Vansh Bansal","submitted_at":"2025-07-22T21:30:06Z","abstract_excerpt":"The two-sample testing problem, a fundamental task in statistics and machine learning, seeks to determine whether two sets of samples, drawn from underlying distributions $p$ and $q$, are in fact identically distributed (i.e. whether $p=q$). A popular and intuitive approach is the classifier two-sample test (C2ST), where a classifier is trained to distinguish between samples from $p$ and $q$. Yet despite simplicity of the C2ST, its reliability hinges on access to a near-Bayes-optimal classifier, a requirement that is rarely met and difficult to verify. This raises a major open question: can a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17026","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.17026/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.17026","created_at":"2026-06-01T02:03:25.004467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17026v2","created_at":"2026-06-01T02:03:25.004467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17026","created_at":"2026-06-01T02:03:25.004467+00:00"},{"alias_kind":"pith_short_12","alias_value":"BR6WF6OLPS5D","created_at":"2026-06-01T02:03:25.004467+00:00"},{"alias_kind":"pith_short_16","alias_value":"BR6WF6OLPS5D4QAB","created_at":"2026-06-01T02:03:25.004467+00:00"},{"alias_kind":"pith_short_8","alias_value":"BR6WF6OL","created_at":"2026-06-01T02:03:25.004467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB","json":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB.json","graph_json":"https://pith.science/api/pith-number/BR6WF6OLPS5D4QABJQZCSSMYKB/graph.json","events_json":"https://pith.science/api/pith-number/BR6WF6OLPS5D4QABJQZCSSMYKB/events.json","paper":"https://pith.science/paper/BR6WF6OL"},"agent_actions":{"view_html":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB","download_json":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB.json","view_paper":"https://pith.science/paper/BR6WF6OL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17026&json=true","fetch_graph":"https://pith.science/api/pith-number/BR6WF6OLPS5D4QABJQZCSSMYKB/graph.json","fetch_events":"https://pith.science/api/pith-number/BR6WF6OLPS5D4QABJQZCSSMYKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB/action/storage_attestation","attest_author":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB/action/author_attestation","sign_citation":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB/action/citation_signature","submit_replication":"https://pith.science/pith/BR6WF6OLPS5D4QABJQZCSSMYKB/action/replication_record"}},"created_at":"2026-06-01T02:03:25.004467+00:00","updated_at":"2026-06-01T02:03:25.004467+00:00"}