{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O3TLDHFJ6TL5BKDTPVBPAC3F5B","short_pith_number":"pith:O3TLDHFJ","schema_version":"1.0","canonical_sha256":"76e6b19ca9f4d7d0a8737d42f00b65e85d24726512564949369d25969230cf7b","source":{"kind":"arxiv","id":"2604.04199","version":2},"attestation_state":"computed","paper":{"title":"Which Leakage Types Matter? A Quantitative Landscape Across 2,047 Benchmark Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Simon Roth","submitted_at":"2026-04-05T17:47:46Z","abstract_excerpt":"Twenty-eight within-subject counterfactual experiments across 2,047 iid tabular datasets, plus a boundary experiment on 129 temporal datasets, measure the severity of four data leakage classes in machine learning. Class I (estimation: fitting scalers on full data) is negligible: all nine conditions produce $|{\\Delta}AUC| \\leq 0.005$. Class II (selection: peeking, seed cherry-picking) is substantial: the measured effect is consistent with about 90% noise exploitation inflating reported scores. Class III (memorization) scales with model capacity: $d_z$ = 0.37 (Naive Bayes) to 1.11 (Decision Tree"},"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":"2604.04199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"48d1c303ad9990dedeb1a5701ed7660ab1d317516f36de907ad456bc79a85fd4","abstract_canon_sha256":"4ee20ff908e817abd5cfdeefb807cc2b52f05602269cf495274e6c66df84d7d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:46.726528Z","signature_b64":"JUaiNZUJLSIWz40PLCcS1sTNje9hR+l0T9l6CJNiXnv0hzQsEhninXYiW0vSxpUOIpJU5MpC22zBFznT5g2XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76e6b19ca9f4d7d0a8737d42f00b65e85d24726512564949369d25969230cf7b","last_reissued_at":"2026-06-02T01:03:46.725891Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:46.725891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Which Leakage Types Matter? A Quantitative Landscape Across 2,047 Benchmark Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Simon Roth","submitted_at":"2026-04-05T17:47:46Z","abstract_excerpt":"Twenty-eight within-subject counterfactual experiments across 2,047 iid tabular datasets, plus a boundary experiment on 129 temporal datasets, measure the severity of four data leakage classes in machine learning. Class I (estimation: fitting scalers on full data) is negligible: all nine conditions produce $|{\\Delta}AUC| \\leq 0.005$. Class II (selection: peeking, seed cherry-picking) is substantial: the measured effect is consistent with about 90% noise exploitation inflating reported scores. Class III (memorization) scales with model capacity: $d_z$ = 0.37 (Naive Bayes) to 1.11 (Decision Tree"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.04199","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/2604.04199/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":"2604.04199","created_at":"2026-06-02T01:03:46.725990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.04199v2","created_at":"2026-06-02T01:03:46.725990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04199","created_at":"2026-06-02T01:03:46.725990+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3TLDHFJ6TL5","created_at":"2026-06-02T01:03:46.725990+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3TLDHFJ6TL5BKDT","created_at":"2026-06-02T01:03:46.725990+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3TLDHFJ","created_at":"2026-06-02T01:03:46.725990+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/O3TLDHFJ6TL5BKDTPVBPAC3F5B","json":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B.json","graph_json":"https://pith.science/api/pith-number/O3TLDHFJ6TL5BKDTPVBPAC3F5B/graph.json","events_json":"https://pith.science/api/pith-number/O3TLDHFJ6TL5BKDTPVBPAC3F5B/events.json","paper":"https://pith.science/paper/O3TLDHFJ"},"agent_actions":{"view_html":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B","download_json":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B.json","view_paper":"https://pith.science/paper/O3TLDHFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.04199&json=true","fetch_graph":"https://pith.science/api/pith-number/O3TLDHFJ6TL5BKDTPVBPAC3F5B/graph.json","fetch_events":"https://pith.science/api/pith-number/O3TLDHFJ6TL5BKDTPVBPAC3F5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B/action/storage_attestation","attest_author":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B/action/author_attestation","sign_citation":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B/action/citation_signature","submit_replication":"https://pith.science/pith/O3TLDHFJ6TL5BKDTPVBPAC3F5B/action/replication_record"}},"created_at":"2026-06-02T01:03:46.725990+00:00","updated_at":"2026-06-02T01:03:46.725990+00:00"}