{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LCJRVSBSEJZAYBLMN6RL3N5ZR2","short_pith_number":"pith:LCJRVSBS","schema_version":"1.0","canonical_sha256":"58931ac83222720c056c6fa2bdb7b98ebecdeb2841e80eb4854f0a408ed75f8f","source":{"kind":"arxiv","id":"2406.12950","version":2},"attestation_state":"computed","paper":{"title":"MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Qiaoyu Tan, Sheng Zhou, Sirui Ding, Wenqi Fan, Yuyan Liu","submitted_at":"2024-06-18T12:54:47Z","abstract_excerpt":"Molecular property prediction (MPP) is a fundamental and crucial task in drug discovery. However, prior methods are limited by the requirement for a large number of labeled molecules and their restricted ability to generalize for unseen and new tasks, both of which are essential for real-world applications. To address these challenges, we present MolecularGPT for few-shot MPP. From a perspective on instruction tuning, we fine-tune large language models (LLMs) based on curated molecular instructions spanning over 1000 property prediction tasks. This enables building a versatile and specialized "},"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":"2406.12950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-06-18T12:54:47Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"title_canon_sha256":"0d6592c25ab24c81cd0a7d73e94a6f6e4cdb1e7f437d4a21750049a51a14594b","abstract_canon_sha256":"efec184b74ca086af2f29dd8406cfc2c560479834eded00b5352daf2b120cfdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:19.723011Z","signature_b64":"avTRmfIqaZOgTzMh2EefvGLPKO8ZmvHGnxeL0N7YCUCkB/Hfd0CxhRPh1ItiYcXkRNVFqnbtAU/XAMixXbWdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58931ac83222720c056c6fa2bdb7b98ebecdeb2841e80eb4854f0a408ed75f8f","last_reissued_at":"2026-07-05T09:22:19.722502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:19.722502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Qiaoyu Tan, Sheng Zhou, Sirui Ding, Wenqi Fan, Yuyan Liu","submitted_at":"2024-06-18T12:54:47Z","abstract_excerpt":"Molecular property prediction (MPP) is a fundamental and crucial task in drug discovery. However, prior methods are limited by the requirement for a large number of labeled molecules and their restricted ability to generalize for unseen and new tasks, both of which are essential for real-world applications. To address these challenges, we present MolecularGPT for few-shot MPP. From a perspective on instruction tuning, we fine-tune large language models (LLMs) based on curated molecular instructions spanning over 1000 property prediction tasks. This enables building a versatile and specialized "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12950","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/2406.12950/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":"2406.12950","created_at":"2026-07-05T09:22:19.722562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12950v2","created_at":"2026-07-05T09:22:19.722562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12950","created_at":"2026-07-05T09:22:19.722562+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCJRVSBSEJZA","created_at":"2026-07-05T09:22:19.722562+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCJRVSBSEJZAYBLM","created_at":"2026-07-05T09:22:19.722562+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCJRVSBS","created_at":"2026-07-05T09:22:19.722562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08723","citing_title":"From Text to Discovery: How Large Language Models Are Reshaping Research Across Scientific and Humanistic Disciplines","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10503","citing_title":"SLASH the Sink: Sharpening Structural Attention Inside LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":265,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10503","citing_title":"SLASH the Sink: Sharpening Structural Attention Inside LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10503","citing_title":"SLASH the Sink: Sharpening Structural Attention Inside LLMs","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2","json":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2.json","graph_json":"https://pith.science/api/pith-number/LCJRVSBSEJZAYBLMN6RL3N5ZR2/graph.json","events_json":"https://pith.science/api/pith-number/LCJRVSBSEJZAYBLMN6RL3N5ZR2/events.json","paper":"https://pith.science/paper/LCJRVSBS"},"agent_actions":{"view_html":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2","download_json":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2.json","view_paper":"https://pith.science/paper/LCJRVSBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12950&json=true","fetch_graph":"https://pith.science/api/pith-number/LCJRVSBSEJZAYBLMN6RL3N5ZR2/graph.json","fetch_events":"https://pith.science/api/pith-number/LCJRVSBSEJZAYBLMN6RL3N5ZR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2/action/storage_attestation","attest_author":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2/action/author_attestation","sign_citation":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2/action/citation_signature","submit_replication":"https://pith.science/pith/LCJRVSBSEJZAYBLMN6RL3N5ZR2/action/replication_record"}},"created_at":"2026-07-05T09:22:19.722562+00:00","updated_at":"2026-07-05T09:22:19.722562+00:00"}