{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:25OCLWZQR6CALMSDS42EWX3PDE","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":"29fe74a7fbfc57116b78599c22067aba69490f88b0d9ca1f94cefa052391b9e0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-06-30T19:53:33Z","title_canon_sha256":"fb5f44cff87faae502258e68fa5cd53fd3103dbea16087fe607d7bd644bc115a"},"schema_version":"1.0","source":{"id":"2607.19376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19376","created_at":"2026-07-23T00:23:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19376v1","created_at":"2026-07-23T00:23:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19376","created_at":"2026-07-23T00:23:46Z"},{"alias_kind":"pith_short_12","alias_value":"25OCLWZQR6CA","created_at":"2026-07-23T00:23:46Z"},{"alias_kind":"pith_short_16","alias_value":"25OCLWZQR6CALMSD","created_at":"2026-07-23T00:23:46Z"},{"alias_kind":"pith_short_8","alias_value":"25OCLWZQ","created_at":"2026-07-23T00:23:46Z"}],"graph_snapshots":[{"event_id":"sha256:3e609904bdbe759b1347f4c8a350f20b2616d3b9e3b725c584e076f5b2410c43","target":"graph","created_at":"2026-07-23T00:23:46Z","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/2607.19376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning models trained on biochemical data are routinely evaluated using splits that fail to account for relational structure, causing information leakage and over-optimistic performance estimates. Existing splitting methods lack theoretical grounding and scale at best quadratically. We introduce the Relational Generative Process (RGP), a mathematical formalization explaining why relational structure arises in biochemical datasets, and Refnd, a splitting algorithm that leverages a proximity graph computed in loglinear time using Hierarchical Navigable Small World (HNSW). We validate o","authors_text":"Anthony Lavertu, Jacob Cote, Jacques Corbeil, Pascal Germain, Sophie Gobeil","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-06-30T19:53:33Z","title":"Refnd: Preventing Data Leakage in Relational Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19376","kind":"arxiv","version":1},"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":"sha256:43c3585ca2d1036f67a5a76765bdf5025d5f50ea88c4bac98395f4fb873cbf39","target":"record","created_at":"2026-07-23T00:23:46Z","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":"29fe74a7fbfc57116b78599c22067aba69490f88b0d9ca1f94cefa052391b9e0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-06-30T19:53:33Z","title_canon_sha256":"fb5f44cff87faae502258e68fa5cd53fd3103dbea16087fe607d7bd644bc115a"},"schema_version":"1.0","source":{"id":"2607.19376","kind":"arxiv","version":1}},"canonical_sha256":"d75c25db308f8405b24397344b5f6f190d2d9d3d55b581c52bb30cf362714cfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d75c25db308f8405b24397344b5f6f190d2d9d3d55b581c52bb30cf362714cfb","first_computed_at":"2026-07-23T00:23:46.811972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T00:23:46.811972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KfDm5QymbKpiAmaACyj2sExgMPGw6B3QJDY50YFaa3jZDJ48CxIzibJ/lnmmDoa09W33MBG4pLcL1YV8bqBrBg==","signature_status":"signed_v1","signed_at":"2026-07-23T00:23:46.812844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43c3585ca2d1036f67a5a76765bdf5025d5f50ea88c4bac98395f4fb873cbf39","sha256:3e609904bdbe759b1347f4c8a350f20b2616d3b9e3b725c584e076f5b2410c43"],"state_sha256":"a9fe061532dccd0583c574a5c405a9c1181b67128e2138db8256848a0c0da737"}