{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AWCHSFJ5JTKRQFGUEN7Z2VBQXO","short_pith_number":"pith:AWCHSFJ5","schema_version":"1.0","canonical_sha256":"058479153d4cd51814d4237f9d5430bb92e51666dcd3879c31bf3b71da50d227","source":{"kind":"arxiv","id":"2310.00174","version":1},"attestation_state":"computed","paper":{"title":"ADMET property prediction through combinations of molecular fingerprints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"James H. Notwell, Michael W. Wood","submitted_at":"2023-09-29T22:39:18Z","abstract_excerpt":"While investigating methods to predict small molecule potencies, we found random forests or support vector machines paired with extended-connectivity fingerprints (ECFP) consistently outperformed recently developed methods. A detailed investigation into regression algorithms and molecular fingerprints revealed gradient-boosted decision trees, particularly CatBoost, in conjunction with a combination of ECFP, Avalon, and ErG fingerprints, as well as 200 molecular properties, to be most effective. Incorporating a graph neural network fingerprint further enhanced performance. We successfully valid"},"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":"2310.00174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-09-29T22:39:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3894f1e585fe39259738e7a0a88ad5706ea3d72e1354868db6e292b86f7b1ae","abstract_canon_sha256":"877f5046d6bf55e20532986524396f0c0c2db63bf13cc2d7ddf6dbd31e58605f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:02.255079Z","signature_b64":"+HEdwdkQi+eG9HCtEkdKMQUha9XJhpRJ8hWD500rpvmFWM7DOIBvQQ42mbGGg1lcQ4HSJZM7Heo7IAGiuGR9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058479153d4cd51814d4237f9d5430bb92e51666dcd3879c31bf3b71da50d227","last_reissued_at":"2026-07-05T06:56:02.254664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:02.254664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADMET property prediction through combinations of molecular fingerprints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"James H. Notwell, Michael W. Wood","submitted_at":"2023-09-29T22:39:18Z","abstract_excerpt":"While investigating methods to predict small molecule potencies, we found random forests or support vector machines paired with extended-connectivity fingerprints (ECFP) consistently outperformed recently developed methods. A detailed investigation into regression algorithms and molecular fingerprints revealed gradient-boosted decision trees, particularly CatBoost, in conjunction with a combination of ECFP, Avalon, and ErG fingerprints, as well as 200 molecular properties, to be most effective. Incorporating a graph neural network fingerprint further enhanced performance. We successfully valid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00174","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/2310.00174/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":"2310.00174","created_at":"2026-07-05T06:56:02.254720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00174v1","created_at":"2026-07-05T06:56:02.254720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00174","created_at":"2026-07-05T06:56:02.254720+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWCHSFJ5JTKR","created_at":"2026-07-05T06:56:02.254720+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWCHSFJ5JTKRQFGU","created_at":"2026-07-05T06:56:02.254720+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWCHSFJ5","created_at":"2026-07-05T06:56:02.254720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22731","citing_title":"Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO","json":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO.json","graph_json":"https://pith.science/api/pith-number/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/graph.json","events_json":"https://pith.science/api/pith-number/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/events.json","paper":"https://pith.science/paper/AWCHSFJ5"},"agent_actions":{"view_html":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO","download_json":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO.json","view_paper":"https://pith.science/paper/AWCHSFJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00174&json=true","fetch_graph":"https://pith.science/api/pith-number/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/graph.json","fetch_events":"https://pith.science/api/pith-number/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/action/storage_attestation","attest_author":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/action/author_attestation","sign_citation":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/action/citation_signature","submit_replication":"https://pith.science/pith/AWCHSFJ5JTKRQFGUEN7Z2VBQXO/action/replication_record"}},"created_at":"2026-07-05T06:56:02.254720+00:00","updated_at":"2026-07-05T06:56:02.254720+00:00"}