{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RU2XKVNM47AHZXB3XM4366K5WQ","short_pith_number":"pith:RU2XKVNM","schema_version":"1.0","canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","source":{"kind":"arxiv","id":"2403.00791","version":2},"attestation_state":"computed","paper":{"title":"L+M-24: Building a Dataset for Language + Molecules @ ACL 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carl Edwards, Heng Ji, Lawrence Zhao, Qingyun Wang","submitted_at":"2024-02-22T20:11:24Z","abstract_excerpt":"Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the $\\textit{L+M-24}$ dataset, which has been created for the Language + Molec"},"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":"2403.00791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T20:11:24Z","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"title_canon_sha256":"63227982eb1ecc0be26bf4d2792164352f959a3ba5ab86e886dd8e1c51eaea41","abstract_canon_sha256":"7834d0dac9ca6645be37e3a6065d416945bccf435b74b038f6d4d2cf0bae0d9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:14.314999Z","signature_b64":"PbARKSbaneIlCk77sCzxm+hBeWxxgEysuvKM/XfGwvW753duhFPp1mUF5wor9EUcqq1teUKsOCxnbnWZjtjyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","last_reissued_at":"2026-07-05T08:40:14.314498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:14.314498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L+M-24: Building a Dataset for Language + Molecules @ ACL 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carl Edwards, Heng Ji, Lawrence Zhao, Qingyun Wang","submitted_at":"2024-02-22T20:11:24Z","abstract_excerpt":"Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the $\\textit{L+M-24}$ dataset, which has been created for the Language + Molec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00791","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/2403.00791/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":"2403.00791","created_at":"2026-07-05T08:40:14.314555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00791v2","created_at":"2026-07-05T08:40:14.314555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00791","created_at":"2026-07-05T08:40:14.314555+00:00"},{"alias_kind":"pith_short_12","alias_value":"RU2XKVNM47AH","created_at":"2026-07-05T08:40:14.314555+00:00"},{"alias_kind":"pith_short_16","alias_value":"RU2XKVNM47AHZXB3","created_at":"2026-07-05T08:40:14.314555+00:00"},{"alias_kind":"pith_short_8","alias_value":"RU2XKVNM","created_at":"2026-07-05T08:40:14.314555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07833","citing_title":"Improving Large Language Models with Concept-Aware Fine-Tuning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ","json":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ.json","graph_json":"https://pith.science/api/pith-number/RU2XKVNM47AHZXB3XM4366K5WQ/graph.json","events_json":"https://pith.science/api/pith-number/RU2XKVNM47AHZXB3XM4366K5WQ/events.json","paper":"https://pith.science/paper/RU2XKVNM"},"agent_actions":{"view_html":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ","download_json":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ.json","view_paper":"https://pith.science/paper/RU2XKVNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00791&json=true","fetch_graph":"https://pith.science/api/pith-number/RU2XKVNM47AHZXB3XM4366K5WQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RU2XKVNM47AHZXB3XM4366K5WQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/action/storage_attestation","attest_author":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/action/author_attestation","sign_citation":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/action/citation_signature","submit_replication":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/action/replication_record"}},"created_at":"2026-07-05T08:40:14.314555+00:00","updated_at":"2026-07-05T08:40:14.314555+00:00"}