{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:23HOTS6VTDX6ATHPZS3C356TXI","short_pith_number":"pith:23HOTS6V","canonical_record":{"source":{"id":"2507.21404","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T00:23:45Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"f36933f8ffd70c4e727af3ea4d58500ded97ef8b48a17202f9769b16d080fed2","abstract_canon_sha256":"f5ac561e5d14a4a5ec8691e8a02ce2d860e32d84dc02aa8b20f874de92739e44"},"schema_version":"1.0"},"canonical_sha256":"d6cee9cbd598efe04cefccb62df7d3ba33b363abccbc8e985d470d788c80cebf","source":{"kind":"arxiv","id":"2507.21404","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21404","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21404v2","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21404","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"23HOTS6VTDX6","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"23HOTS6VTDX6ATHP","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"23HOTS6V","created_at":"2026-07-05T11:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:23HOTS6VTDX6ATHPZS3C356TXI","target":"record","payload":{"canonical_record":{"source":{"id":"2507.21404","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T00:23:45Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"f36933f8ffd70c4e727af3ea4d58500ded97ef8b48a17202f9769b16d080fed2","abstract_canon_sha256":"f5ac561e5d14a4a5ec8691e8a02ce2d860e32d84dc02aa8b20f874de92739e44"},"schema_version":"1.0"},"canonical_sha256":"d6cee9cbd598efe04cefccb62df7d3ba33b363abccbc8e985d470d788c80cebf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:58.429623Z","signature_b64":"xN6KFCfFbJrBiylRIyJt/dX1V9grCk0U0ujZGno6C0YPLXlHQeN17ZiW+kU1zxEzt9W8d7tpY73IDKxIEY72BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6cee9cbd598efe04cefccb62df7d3ba33b363abccbc8e985d470d788c80cebf","last_reissued_at":"2026-07-05T11:49:58.429191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:58.429191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.21404","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2CwVZ9H8Bp9giVC9rvrbl4XPHfoFht4PwPO1ASnDitnJFKi7R5W9MPtxX+34QFda9Umrv/MoGEfdCKHx8s6kAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:56:32.085143Z"},"content_sha256":"3f80c2162f6efc6d50fbf85b28b5ffb91e713edf73df9458278a216005f67798","schema_version":"1.0","event_id":"sha256:3f80c2162f6efc6d50fbf85b28b5ffb91e713edf73df9458278a216005f67798"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:23HOTS6VTDX6ATHPZS3C356TXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Leakage and Redundancy in the LIT-PCBA Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Amber Huang, Ian Scott Knight, Slava Naprienko","submitted_at":"2025-07-29T00:23:45Z","abstract_excerpt":"LIT-PCBA is widely used to benchmark virtual screening models, but our audit reveals that it is fundamentally compromised. We find extensive data leakage and molecular redundancy across its splits, including 2D-identical ligands within and across partitions, pervasive analog overlap, and low-diversity query sets. In ALDH1 alone, for instance, 323 active training -- validation analog pairs occur at ECFP4 Tanimoto similarity $\\geq 0.6$; across all targets, 2,491 2D-identical inactives appear in both training and validation, with very few corresponding actives. These overlaps allow models to succ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21404","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/2507.21404/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cr7tgB212Zapo2p2pfx3pFcZgwiUJMLsZg2Fn1qN5hJCFA8by9FkX/2myqtQLjB2xQ8RcOkWVC8KJ7+leAIMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:56:32.085657Z"},"content_sha256":"bcada9a4056d714f1cf6b77117939b0c2f8af2d3e7810e5cb23fddc2beb6e409","schema_version":"1.0","event_id":"sha256:bcada9a4056d714f1cf6b77117939b0c2f8af2d3e7810e5cb23fddc2beb6e409"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23HOTS6VTDX6ATHPZS3C356TXI/bundle.json","state_url":"https://pith.science/pith/23HOTS6VTDX6ATHPZS3C356TXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23HOTS6VTDX6ATHPZS3C356TXI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T22:56:32Z","links":{"resolver":"https://pith.science/pith/23HOTS6VTDX6ATHPZS3C356TXI","bundle":"https://pith.science/pith/23HOTS6VTDX6ATHPZS3C356TXI/bundle.json","state":"https://pith.science/pith/23HOTS6VTDX6ATHPZS3C356TXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23HOTS6VTDX6ATHPZS3C356TXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:23HOTS6VTDX6ATHPZS3C356TXI","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":"f5ac561e5d14a4a5ec8691e8a02ce2d860e32d84dc02aa8b20f874de92739e44","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T00:23:45Z","title_canon_sha256":"f36933f8ffd70c4e727af3ea4d58500ded97ef8b48a17202f9769b16d080fed2"},"schema_version":"1.0","source":{"id":"2507.21404","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21404","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21404v2","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21404","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"23HOTS6VTDX6","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"23HOTS6VTDX6ATHP","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"23HOTS6V","created_at":"2026-07-05T11:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:bcada9a4056d714f1cf6b77117939b0c2f8af2d3e7810e5cb23fddc2beb6e409","target":"graph","created_at":"2026-07-05T11:49:58Z","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/2507.21404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LIT-PCBA is widely used to benchmark virtual screening models, but our audit reveals that it is fundamentally compromised. We find extensive data leakage and molecular redundancy across its splits, including 2D-identical ligands within and across partitions, pervasive analog overlap, and low-diversity query sets. In ALDH1 alone, for instance, 323 active training -- validation analog pairs occur at ECFP4 Tanimoto similarity $\\geq 0.6$; across all targets, 2,491 2D-identical inactives appear in both training and validation, with very few corresponding actives. These overlaps allow models to succ","authors_text":"Amber Huang, Ian Scott Knight, Slava Naprienko","cross_cats":["q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T00:23:45Z","title":"Data Leakage and Redundancy in the LIT-PCBA Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21404","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":"sha256:3f80c2162f6efc6d50fbf85b28b5ffb91e713edf73df9458278a216005f67798","target":"record","created_at":"2026-07-05T11:49:58Z","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":"f5ac561e5d14a4a5ec8691e8a02ce2d860e32d84dc02aa8b20f874de92739e44","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T00:23:45Z","title_canon_sha256":"f36933f8ffd70c4e727af3ea4d58500ded97ef8b48a17202f9769b16d080fed2"},"schema_version":"1.0","source":{"id":"2507.21404","kind":"arxiv","version":2}},"canonical_sha256":"d6cee9cbd598efe04cefccb62df7d3ba33b363abccbc8e985d470d788c80cebf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6cee9cbd598efe04cefccb62df7d3ba33b363abccbc8e985d470d788c80cebf","first_computed_at":"2026-07-05T11:49:58.429191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:58.429191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xN6KFCfFbJrBiylRIyJt/dX1V9grCk0U0ujZGno6C0YPLXlHQeN17ZiW+kU1zxEzt9W8d7tpY73IDKxIEY72BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:58.429623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21404","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f80c2162f6efc6d50fbf85b28b5ffb91e713edf73df9458278a216005f67798","sha256:bcada9a4056d714f1cf6b77117939b0c2f8af2d3e7810e5cb23fddc2beb6e409"],"state_sha256":"feed504eb71c36c3435f2aaf7f64d584a7ac1e27702aff277f650de1b5eaad4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3Ru4bgA1q3iCshfecY3VPZl+EAWceoMS0laGSRqFrtWcoQy8l0lPC8ldYYyWXEMUXm0q2WFactkdZInoFH9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T22:56:32.090833Z","bundle_sha256":"926436e98996b548c8d6128539f9b6a7b68a5afcb7740ec2f6341943411f1e0f"}}