{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EUPNQL2TNG5LOY2POKAJ7UP3CW","short_pith_number":"pith:EUPNQL2T","schema_version":"1.0","canonical_sha256":"251ed82f5369bab7634f72809fd1fb158b7727a49d2ec893c4d5ee0d7f54acd2","source":{"kind":"arxiv","id":"2502.13398","version":2},"attestation_state":"computed","paper":{"title":"GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","physics.chem-ph","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Vishal Dey, Xia Ning, Xiao Hu","submitted_at":"2025-02-19T03:14:11Z","abstract_excerpt":"Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs' potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on complex multi-property molecule optimization tasks. Leveraging MuMOInstruct, we develop GeLLMOs, a se"},"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":"2502.13398","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T03:14:11Z","cross_cats_sorted":["cs.AI","cs.CL","physics.chem-ph","q-bio.QM"],"title_canon_sha256":"10f5a0fee9e42dc83798cef943e08671ad7cbefc0fced1f56d24f2a8e60fd9d9","abstract_canon_sha256":"aea69bbbcf07a50ea0a559449bd3772dfab7546cd69073d90e0aafc21df048d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:35.459696Z","signature_b64":"NJklR4hS10WNhfzL72FpTtURUwlX9oBtf5RKrd9bnzRntLSEAEzDZ8115NolhTKdaBtUK1aWM1AmrGWVNy8XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"251ed82f5369bab7634f72809fd1fb158b7727a49d2ec893c4d5ee0d7f54acd2","last_reissued_at":"2026-07-05T11:10:35.459144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:35.459144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","physics.chem-ph","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Vishal Dey, Xia Ning, Xiao Hu","submitted_at":"2025-02-19T03:14:11Z","abstract_excerpt":"Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs' potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on complex multi-property molecule optimization tasks. Leveraging MuMOInstruct, we develop GeLLMOs, a se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13398","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.13398/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":"2502.13398","created_at":"2026-07-05T11:10:35.459205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13398v2","created_at":"2026-07-05T11:10:35.459205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13398","created_at":"2026-07-05T11:10:35.459205+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUPNQL2TNG5L","created_at":"2026-07-05T11:10:35.459205+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUPNQL2TNG5LOY2P","created_at":"2026-07-05T11:10:35.459205+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUPNQL2T","created_at":"2026-07-05T11:10:35.459205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28862","citing_title":"Molecular Lead Optimization via Agentic Tool Planning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10831","citing_title":"SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW","json":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW.json","graph_json":"https://pith.science/api/pith-number/EUPNQL2TNG5LOY2POKAJ7UP3CW/graph.json","events_json":"https://pith.science/api/pith-number/EUPNQL2TNG5LOY2POKAJ7UP3CW/events.json","paper":"https://pith.science/paper/EUPNQL2T"},"agent_actions":{"view_html":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW","download_json":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW.json","view_paper":"https://pith.science/paper/EUPNQL2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13398&json=true","fetch_graph":"https://pith.science/api/pith-number/EUPNQL2TNG5LOY2POKAJ7UP3CW/graph.json","fetch_events":"https://pith.science/api/pith-number/EUPNQL2TNG5LOY2POKAJ7UP3CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW/action/storage_attestation","attest_author":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW/action/author_attestation","sign_citation":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW/action/citation_signature","submit_replication":"https://pith.science/pith/EUPNQL2TNG5LOY2POKAJ7UP3CW/action/replication_record"}},"created_at":"2026-07-05T11:10:35.459205+00:00","updated_at":"2026-07-05T11:10:35.459205+00:00"}