{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IFPRI4MWNBNOQAL4SQRKMVYO7H","short_pith_number":"pith:IFPRI4MW","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"},"canonical_sha256":"415f147196685ae8017c9422a6570ef9f202c8d6502131b15975a335684dd6c9","source":{"kind":"arxiv","id":"2505.16094","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16094","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16094v1","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16094","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"IFPRI4MWNBNO","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_16","alias_value":"IFPRI4MWNBNOQAL4","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_8","alias_value":"IFPRI4MW","created_at":"2026-07-05T11:07:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IFPRI4MWNBNOQAL4SQRKMVYO7H","target":"record","payload":{"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"},"canonical_sha256":"415f147196685ae8017c9422a6570ef9f202c8d6502131b15975a335684dd6c9","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"},"source_kind":"arxiv","source_id":"2505.16094","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8R0MYTkfJ4wxcgwQeJbmwBife8zzQSaBIQXksrr44mFHEQFUrD/5bEMAnSIXUQH7E9BVIMY+esE1OJbLnKHIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:48:44.821811Z"},"content_sha256":"bf99c3ef8c578edaa4c87e56586b68c93759e56b4fa6d2b6152c636e43ead384","schema_version":"1.0","event_id":"sha256:bf99c3ef8c578edaa4c87e56586b68c93759e56b4fa6d2b6152c636e43ead384"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IFPRI4MWNBNOQAL4SQRKMVYO7H","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/B/G7ZIDsH2T0aZ4+IY6Dl9px7oLnSmyu3xCXINCFxB4S0P2Ugu57e8fi8g8x4DLV6l9OyXOAOcMCNQhp7bBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:48:44.822387Z"},"content_sha256":"ed561b341ac9c0182e17e3b73b7e7d34b9020f1e96eb918efec6cdc204eaf38a","schema_version":"1.0","event_id":"sha256:ed561b341ac9c0182e17e3b73b7e7d34b9020f1e96eb918efec6cdc204eaf38a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/bundle.json","state_url":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T07:48:44Z","links":{"resolver":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H","bundle":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/bundle.json","state":"https://pith.science/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFPRI4MWNBNOQAL4SQRKMVYO7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IFPRI4MWNBNOQAL4SQRKMVYO7H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"31a87eaad645a854e6d23b8801eee366e8d742490656851023486265ff41ac30","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T00:26:27Z","title_canon_sha256":"766ac8d6a866d78ba34ecac3d7f197d5cb26ec33893868c0def8cfb5266da6f2"},"schema_version":"1.0","source":{"id":"2505.16094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16094","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16094v1","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16094","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"IFPRI4MWNBNO","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_16","alias_value":"IFPRI4MWNBNOQAL4","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_8","alias_value":"IFPRI4MW","created_at":"2026-07-05T11:07:29Z"}],"graph_snapshots":[{"event_id":"sha256:ed561b341ac9c0182e17e3b73b7e7d34b9020f1e96eb918efec6cdc204eaf38a","target":"graph","created_at":"2026-07-05T11:07:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhishek Pandey, Han Liu, Kaize Ding, Kexin Zhang, Yibo Wen, Zihan Zhao, Ziqing Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T00:26:27Z","title":"A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16094","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf99c3ef8c578edaa4c87e56586b68c93759e56b4fa6d2b6152c636e43ead384","target":"record","created_at":"2026-07-05T11:07:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"31a87eaad645a854e6d23b8801eee366e8d742490656851023486265ff41ac30","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T00:26:27Z","title_canon_sha256":"766ac8d6a866d78ba34ecac3d7f197d5cb26ec33893868c0def8cfb5266da6f2"},"schema_version":"1.0","source":{"id":"2505.16094","kind":"arxiv","version":1}},"canonical_sha256":"415f147196685ae8017c9422a6570ef9f202c8d6502131b15975a335684dd6c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"415f147196685ae8017c9422a6570ef9f202c8d6502131b15975a335684dd6c9","first_computed_at":"2026-07-05T11:07:29.782404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:29.782404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ljH7BmIUWOsYwng5JgMQb2tTNtFsY8Sp2SRdZ0F78BEQai0PRBmLCAPWeF1VeMt7YRBiBaRekvcopgSmxF+hBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:29.782973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16094","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf99c3ef8c578edaa4c87e56586b68c93759e56b4fa6d2b6152c636e43ead384","sha256:ed561b341ac9c0182e17e3b73b7e7d34b9020f1e96eb918efec6cdc204eaf38a"],"state_sha256":"940cc494205208f8d75b7fc057951f44176b0162eb41fcc6e59657c350cc6be8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E63BhUDyL1fOQXr0RZEI3gLQ6up0y9ECcSJPvMqgijuEkvbBOzcmdpoTj+HvGqNbPSCUKRqvLQMQcg2Zli9XCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:48:44.826034Z","bundle_sha256":"7ba1c351011873b0cf456244fcabf95937ad0cfbc2f8c669db4f8f2a2613c528"}}