{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7L7DXX5ZJHRULA4VL7RMW6FCF3","short_pith_number":"pith:7L7DXX5Z","schema_version":"1.0","canonical_sha256":"fafe3bdfb949e34583955fe2cb78a22ed15ab2cb33740d04a41d9fc8e79fcc5f","source":{"kind":"arxiv","id":"1706.06619","version":2},"attestation_state":"computed","paper":{"title":"Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.QM","authors_text":"Abraham Heifets, Izhar Wallach","submitted_at":"2017-06-20T18:47:46Z","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 "},"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":"1706.06619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2017-06-20T18:47:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fc0e3ad8d6b76079adaa0d96f4d70fbc021da4faf97c1cefb5722993493437ed","abstract_canon_sha256":"5b73c3c0f16e6876e79378e10f751460f2d6dc3d19bb16cb44ffe57325749b10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:19.494835Z","signature_b64":"M5niX7zcT2cVU/wm0bzKwjoB1FXVaEcNly3BnnIILguG19MJMAhVnQw2B7n++d06PChhCJzGSzWyF3i/VgLvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fafe3bdfb949e34583955fe2cb78a22ed15ab2cb33740d04a41d9fc8e79fcc5f","last_reissued_at":"2026-05-18T00:16:19.494389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:19.494389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.QM","authors_text":"Abraham Heifets, Izhar Wallach","submitted_at":"2017-06-20T18:47:46Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06619","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":""},"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":"1706.06619","created_at":"2026-05-18T00:16:19.494462+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.06619v2","created_at":"2026-05-18T00:16:19.494462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06619","created_at":"2026-05-18T00:16:19.494462+00:00"},{"alias_kind":"pith_short_12","alias_value":"7L7DXX5ZJHRU","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7L7DXX5ZJHRULA4V","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7L7DXX5Z","created_at":"2026-05-18T12:31:05.417338+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/7L7DXX5ZJHRULA4VL7RMW6FCF3","json":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3.json","graph_json":"https://pith.science/api/pith-number/7L7DXX5ZJHRULA4VL7RMW6FCF3/graph.json","events_json":"https://pith.science/api/pith-number/7L7DXX5ZJHRULA4VL7RMW6FCF3/events.json","paper":"https://pith.science/paper/7L7DXX5Z"},"agent_actions":{"view_html":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3","download_json":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3.json","view_paper":"https://pith.science/paper/7L7DXX5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.06619&json=true","fetch_graph":"https://pith.science/api/pith-number/7L7DXX5ZJHRULA4VL7RMW6FCF3/graph.json","fetch_events":"https://pith.science/api/pith-number/7L7DXX5ZJHRULA4VL7RMW6FCF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3/action/storage_attestation","attest_author":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3/action/author_attestation","sign_citation":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3/action/citation_signature","submit_replication":"https://pith.science/pith/7L7DXX5ZJHRULA4VL7RMW6FCF3/action/replication_record"}},"created_at":"2026-05-18T00:16:19.494462+00:00","updated_at":"2026-05-18T00:16:19.494462+00:00"}