{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O3TLDHFJ6TL5BKDTPVBPAC3F5B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4ee20ff908e817abd5cfdeefb807cc2b52f05602269cf495274e6c66df84d7d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:47:46Z","title_canon_sha256":"48d1c303ad9990dedeb1a5701ed7660ab1d317516f36de907ad456bc79a85fd4"},"schema_version":"1.0","source":{"id":"2604.04199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.04199","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2604.04199v2","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04199","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"O3TLDHFJ6TL5","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"O3TLDHFJ6TL5BKDT","created_at":"2026-06-02T01:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"O3TLDHFJ","created_at":"2026-06-02T01:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:5c1179c54c8d4664eeaf0daf2b7e0b80185302b158333eeb6f1a7afebf7e8e6b","target":"graph","created_at":"2026-06-02T01:03:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.04199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Simon Roth","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:47:46Z","title":"Which Leakage Types Matter? A Quantitative Landscape Across 2,047 Benchmark Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.04199","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:314d7e3b2137e245cbee1c2ff5eb2907fbf0fe298a021f4d7975a4a5cf49e6b0","target":"record","created_at":"2026-06-02T01:03:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4ee20ff908e817abd5cfdeefb807cc2b52f05602269cf495274e6c66df84d7d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:47:46Z","title_canon_sha256":"48d1c303ad9990dedeb1a5701ed7660ab1d317516f36de907ad456bc79a85fd4"},"schema_version":"1.0","source":{"id":"2604.04199","kind":"arxiv","version":2}},"canonical_sha256":"76e6b19ca9f4d7d0a8737d42f00b65e85d24726512564949369d25969230cf7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76e6b19ca9f4d7d0a8737d42f00b65e85d24726512564949369d25969230cf7b","first_computed_at":"2026-06-02T01:03:46.725891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:46.725891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JUaiNZUJLSIWz40PLCcS1sTNje9hR+l0T9l6CJNiXnv0hzQsEhninXYiW0vSxpUOIpJU5MpC22zBFznT5g2XCA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:46.726528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.04199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:314d7e3b2137e245cbee1c2ff5eb2907fbf0fe298a021f4d7975a4a5cf49e6b0","sha256:5c1179c54c8d4664eeaf0daf2b7e0b80185302b158333eeb6f1a7afebf7e8e6b"],"state_sha256":"39a5ad1c7c41a046e44f41245ec761acbe21fa7014de787a4bb5900456d654ae"}