{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6QOQIVFHB7E3BOLVTQ2EKMT3OT","short_pith_number":"pith:6QOQIVFH","schema_version":"1.0","canonical_sha256":"f41d0454a70fc9b0b9759c3445327b74c46e83bb1cc713b12deea1e18231638d","source":{"kind":"arxiv","id":"2501.02059","version":1},"attestation_state":"computed","paper":{"title":"Active Learning Enables Extrapolation in Molecular Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Anna M. Hiszpanski, Bhavya Kailkhura, Evan R. Antoniuk, Nathan Keilbart, Peggy Li, Stephen Weitzner","submitted_at":"2025-01-03T19:07:06Z","abstract_excerpt":"Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the known molecules seen in training. We find that a key limitation is not in the molecule generation process itself, but in the poor generalization capabilities of molecular property predictors. We tackle this challenge by creating an active-learning, closed-loop molecule generation pipeline, whereby molecular generative models are iteratively refined on feedback from quantum chemical simulations to improve generalization to "},"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":"2501.02059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-03T19:07:06Z","cross_cats_sorted":["cond-mat.mtrl-sci","physics.chem-ph"],"title_canon_sha256":"b9efa6ec323305bad4706c801cd205bb97196adabb895de3ef5693328cb34550","abstract_canon_sha256":"00570ee577b5663a16365ff3e4b2a4f1ac33c0ebc3c20d43a989db841faaa5a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:01.026122Z","signature_b64":"ViGgUJL/sMPmWbyDzwBgmKEEweZvXdD5tjTBWbZ7mzyRNA6GZZjvgm/mrz47TzvH2utkxDJLWHEcUpifkkdLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f41d0454a70fc9b0b9759c3445327b74c46e83bb1cc713b12deea1e18231638d","last_reissued_at":"2026-07-05T09:57:01.025636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:01.025636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Learning Enables Extrapolation in Molecular Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Anna M. Hiszpanski, Bhavya Kailkhura, Evan R. Antoniuk, Nathan Keilbart, Peggy Li, Stephen Weitzner","submitted_at":"2025-01-03T19:07:06Z","abstract_excerpt":"Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the known molecules seen in training. We find that a key limitation is not in the molecule generation process itself, but in the poor generalization capabilities of molecular property predictors. We tackle this challenge by creating an active-learning, closed-loop molecule generation pipeline, whereby molecular generative models are iteratively refined on feedback from quantum chemical simulations to improve generalization to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02059","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/2501.02059/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":"2501.02059","created_at":"2026-07-05T09:57:01.025694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02059v1","created_at":"2026-07-05T09:57:01.025694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02059","created_at":"2026-07-05T09:57:01.025694+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QOQIVFHB7E3","created_at":"2026-07-05T09:57:01.025694+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QOQIVFHB7E3BOLV","created_at":"2026-07-05T09:57:01.025694+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QOQIVFH","created_at":"2026-07-05T09:57:01.025694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20497","citing_title":"Interpretable Meta-Learning for Multi-Objective Chemical Search","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT","json":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT.json","graph_json":"https://pith.science/api/pith-number/6QOQIVFHB7E3BOLVTQ2EKMT3OT/graph.json","events_json":"https://pith.science/api/pith-number/6QOQIVFHB7E3BOLVTQ2EKMT3OT/events.json","paper":"https://pith.science/paper/6QOQIVFH"},"agent_actions":{"view_html":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT","download_json":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT.json","view_paper":"https://pith.science/paper/6QOQIVFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02059&json=true","fetch_graph":"https://pith.science/api/pith-number/6QOQIVFHB7E3BOLVTQ2EKMT3OT/graph.json","fetch_events":"https://pith.science/api/pith-number/6QOQIVFHB7E3BOLVTQ2EKMT3OT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT/action/storage_attestation","attest_author":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT/action/author_attestation","sign_citation":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT/action/citation_signature","submit_replication":"https://pith.science/pith/6QOQIVFHB7E3BOLVTQ2EKMT3OT/action/replication_record"}},"created_at":"2026-07-05T09:57:01.025694+00:00","updated_at":"2026-07-05T09:57:01.025694+00:00"}