{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7L7DXX5ZJHRULA4VL7RMW6FCF3","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":"5b73c3c0f16e6876e79378e10f751460f2d6dc3d19bb16cb44ffe57325749b10","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2017-06-20T18:47:46Z","title_canon_sha256":"fc0e3ad8d6b76079adaa0d96f4d70fbc021da4faf97c1cefb5722993493437ed"},"schema_version":"1.0","source":{"id":"1706.06619","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06619","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06619v2","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06619","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"7L7DXX5ZJHRU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7L7DXX5ZJHRULA4V","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7L7DXX5Z","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b5b181c3240cf826d514ef61cba18676da60e60953d4c59bc817b3fe0b45d19d","target":"graph","created_at":"2026-05-18T00:16:19Z","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"},"paper":{"abstract_excerpt":"Undetected overfitting can occur when there are significant redundancies between training and validation data. We describe AVE, a new measure of training-validation redundancy for ligand-based classification problems that accounts for the similarity amongst inactive molecules as well as active. We investigated seven widely-used benchmarks for virtual screening and classification, and show that the amount of AVE bias strongly correlates with the performance of ligand-based predictive methods irrespective of the predicted property, chemical fingerprint, similarity measure, or previously-applied ","authors_text":"Abraham Heifets, Izhar Wallach","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2017-06-20T18:47:46Z","title":"Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06619","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:aef489388b73ed3ff76ec0fcf9b6fec4cb4c5d91240f230147e82a16b04395cb","target":"record","created_at":"2026-05-18T00:16:19Z","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":"5b73c3c0f16e6876e79378e10f751460f2d6dc3d19bb16cb44ffe57325749b10","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2017-06-20T18:47:46Z","title_canon_sha256":"fc0e3ad8d6b76079adaa0d96f4d70fbc021da4faf97c1cefb5722993493437ed"},"schema_version":"1.0","source":{"id":"1706.06619","kind":"arxiv","version":2}},"canonical_sha256":"fafe3bdfb949e34583955fe2cb78a22ed15ab2cb33740d04a41d9fc8e79fcc5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fafe3bdfb949e34583955fe2cb78a22ed15ab2cb33740d04a41d9fc8e79fcc5f","first_computed_at":"2026-05-18T00:16:19.494389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:19.494389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M5niX7zcT2cVU/wm0bzKwjoB1FXVaEcNly3BnnIILguG19MJMAhVnQw2B7n++d06PChhCJzGSzWyF3i/VgLvCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:19.494835Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.06619","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aef489388b73ed3ff76ec0fcf9b6fec4cb4c5d91240f230147e82a16b04395cb","sha256:b5b181c3240cf826d514ef61cba18676da60e60953d4c59bc817b3fe0b45d19d"],"state_sha256":"d3334e0eff203cb298595ba25d0341588d980a96aefcb74cf0fc66a5238b9de7"}