{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IFPRI4MWNBNOQAL4SQRKMVYO7H","short_pith_number":"pith:IFPRI4MW","schema_version":"1.0","canonical_sha256":"415f147196685ae8017c9422a6570ef9f202c8d6502131b15975a335684dd6c9","source":{"kind":"arxiv","id":"2505.16094","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Abhishek Pandey, Han Liu, Kaize Ding, Kexin Zhang, Yibo Wen, Zihan Zhao, Ziqing Wang","submitted_at":"2025-05-22T00:26:27Z","abstract_excerpt":"Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language, symbolic notations, with emerging extensions to incorporate multi-modal inputs. To advance the new field of LLM for molecular discovery, this survey provides an up-to-date and forward-looking review of the emerging use of LLMs for two central tasks: molecule generation and molecule optimization. Based on our proposed taxonomy for both problems, we analyze representative techniques in each category, highlighting how LLM capabilit"},"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":"2505.16094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T00:26:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"766ac8d6a866d78ba34ecac3d7f197d5cb26ec33893868c0def8cfb5266da6f2","abstract_canon_sha256":"31a87eaad645a854e6d23b8801eee366e8d742490656851023486265ff41ac30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:29.782973Z","signature_b64":"ljH7BmIUWOsYwng5JgMQb2tTNtFsY8Sp2SRdZ0F78BEQai0PRBmLCAPWeF1VeMt7YRBiBaRekvcopgSmxF+hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"415f147196685ae8017c9422a6570ef9f202c8d6502131b15975a335684dd6c9","last_reissued_at":"2026-07-05T11:07:29.782404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:29.782404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Abhishek Pandey, Han Liu, Kaize Ding, Kexin Zhang, Yibo Wen, Zihan Zhao, Ziqing Wang","submitted_at":"2025-05-22T00:26:27Z","abstract_excerpt":"Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language, symbolic notations, with emerging extensions to incorporate multi-modal inputs. To advance the new field of LLM for molecular discovery, this survey provides an up-to-date and forward-looking review of the emerging use of LLMs for two central tasks: molecule generation and molecule optimization. Based on our proposed taxonomy for both problems, we analyze representative techniques in each category, highlighting how LLM capabilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16094","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/2505.16094/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":"2505.16094","created_at":"2026-07-05T11:07:29.782484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16094v1","created_at":"2026-07-05T11:07:29.782484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16094","created_at":"2026-07-05T11:07:29.782484+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFPRI4MWNBNO","created_at":"2026-07-05T11:07:29.782484+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFPRI4MWNBNOQAL4","created_at":"2026-07-05T11:07:29.782484+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFPRI4MW","created_at":"2026-07-05T11:07:29.782484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17271","citing_title":"HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H","json":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H.json","graph_json":"https://pith.science/api/pith-number/IFPRI4MWNBNOQAL4SQRKMVYO7H/graph.json","events_json":"https://pith.science/api/pith-number/IFPRI4MWNBNOQAL4SQRKMVYO7H/events.json","paper":"https://pith.science/paper/IFPRI4MW"},"agent_actions":{"view_html":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H","download_json":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H.json","view_paper":"https://pith.science/paper/IFPRI4MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16094&json=true","fetch_graph":"https://pith.science/api/pith-number/IFPRI4MWNBNOQAL4SQRKMVYO7H/graph.json","fetch_events":"https://pith.science/api/pith-number/IFPRI4MWNBNOQAL4SQRKMVYO7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/action/storage_attestation","attest_author":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/action/author_attestation","sign_citation":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/action/citation_signature","submit_replication":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/action/replication_record"}},"created_at":"2026-07-05T11:07:29.782484+00:00","updated_at":"2026-07-05T11:07:29.782484+00:00"}