{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EQUBNBNSSIJCQBLGHU2FWC7OYH","short_pith_number":"pith:EQUBNBNS","schema_version":"1.0","canonical_sha256":"24281685b292122805663d345b0beec1e13ff016f70ab06834a6532f5a36e421","source":{"kind":"arxiv","id":"2310.09267","version":1},"attestation_state":"computed","paper":{"title":"Genetic algorithms are strong baselines for molecule generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.NE","authors_text":"Austin Tripp, Jos\\'e Miguel Hern\\'andez-Lobato","submitted_at":"2023-10-13T17:25:11Z","abstract_excerpt":"Generating molecules, both in a directed and undirected fashion, is a huge part of the drug discovery pipeline. Genetic algorithms (GAs) generate molecules by randomly modifying known molecules. In this paper we show that GAs are very strong algorithms for such tasks, outperforming many complicated machine learning methods: a result which many researchers may find surprising. We therefore propose insisting during peer review that new algorithms must have some clear advantage over GAs, which we call the GA criterion. Ultimately our work suggests that a lot of research in molecule generation sho"},"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":"2310.09267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-10-13T17:25:11Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"1d67e75bdd40c9154fdac73216c6fbd5e50cf69ed8124fd27850546d5c193c2c","abstract_canon_sha256":"7199a399bd55e1fc19a80f4f569741d01aee46c694945965304124aec27b38d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:42.063908Z","signature_b64":"//5HrfwuaBvaZcoMmNr6yu+U4qJiLR2rNgZqiAbGii29ubIcfQxRd3ImRxmfKpe0zI2VoMqDDPe+/CI0ud6cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24281685b292122805663d345b0beec1e13ff016f70ab06834a6532f5a36e421","last_reissued_at":"2026-07-05T07:00:42.063438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:42.063438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Genetic algorithms are strong baselines for molecule generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.NE","authors_text":"Austin Tripp, Jos\\'e Miguel Hern\\'andez-Lobato","submitted_at":"2023-10-13T17:25:11Z","abstract_excerpt":"Generating molecules, both in a directed and undirected fashion, is a huge part of the drug discovery pipeline. Genetic algorithms (GAs) generate molecules by randomly modifying known molecules. In this paper we show that GAs are very strong algorithms for such tasks, outperforming many complicated machine learning methods: a result which many researchers may find surprising. We therefore propose insisting during peer review that new algorithms must have some clear advantage over GAs, which we call the GA criterion. Ultimately our work suggests that a lot of research in molecule generation sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09267","kind":"arxiv","version":1},"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/2310.09267/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.09267","created_at":"2026-07-05T07:00:42.063491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09267v1","created_at":"2026-07-05T07:00:42.063491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09267","created_at":"2026-07-05T07:00:42.063491+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQUBNBNSSIJC","created_at":"2026-07-05T07:00:42.063491+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQUBNBNSSIJCQBLG","created_at":"2026-07-05T07:00:42.063491+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQUBNBNS","created_at":"2026-07-05T07:00:42.063491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29161","citing_title":"GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30170","citing_title":"Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH","json":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH.json","graph_json":"https://pith.science/api/pith-number/EQUBNBNSSIJCQBLGHU2FWC7OYH/graph.json","events_json":"https://pith.science/api/pith-number/EQUBNBNSSIJCQBLGHU2FWC7OYH/events.json","paper":"https://pith.science/paper/EQUBNBNS"},"agent_actions":{"view_html":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH","download_json":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH.json","view_paper":"https://pith.science/paper/EQUBNBNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09267&json=true","fetch_graph":"https://pith.science/api/pith-number/EQUBNBNSSIJCQBLGHU2FWC7OYH/graph.json","fetch_events":"https://pith.science/api/pith-number/EQUBNBNSSIJCQBLGHU2FWC7OYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH/action/storage_attestation","attest_author":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH/action/author_attestation","sign_citation":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH/action/citation_signature","submit_replication":"https://pith.science/pith/EQUBNBNSSIJCQBLGHU2FWC7OYH/action/replication_record"}},"created_at":"2026-07-05T07:00:42.063491+00:00","updated_at":"2026-07-05T07:00:42.063491+00:00"}