{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6ODCZRDCYJU7DNADKQKFXDQ76G","short_pith_number":"pith:6ODCZRDC","schema_version":"1.0","canonical_sha256":"f3862cc462c269f1b40354145b8e1ff1b4b785efbeb6aa61ecb7b4756fa90a21","source":{"kind":"arxiv","id":"2307.12996","version":1},"attestation_state":"computed","paper":{"title":"Extracting Molecular Properties from Natural Language with Multimodal Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Andrew Gaut, David L\\\"udeke, Jeff He, Kateryna Pistunova, Romain Lacombe","submitted_at":"2023-07-22T10:32:58Z","abstract_excerpt":"Deep learning in computational biochemistry has traditionally focused on molecular graphs neural representations; however, recent advances in language models highlight how much scientific knowledge is encoded in text. To bridge these two modalities, we investigate how molecular property information can be transferred from natural language to graph representations. We study property prediction performance gains after using contrastive learning to align neural graph representations with representations of textual descriptions of their characteristics. We implement neural relevance scoring strate"},"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":"2307.12996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T10:32:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","q-bio.QM"],"title_canon_sha256":"e2764346edfbd9fb282e3ceeca01fe8cd93431dc2a867dc03e87b5366711f998","abstract_canon_sha256":"62bb37314d50a29df567f4b4ed30e67d1b121831d179d966c0e5c73b5b55165d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:07.641869Z","signature_b64":"NefR3xvSZHJFb3gAthKSzjo3jTGCLo12eMGudFOKysNYhNstjXQfXVD4nuFt5Mp8aqvNFeUbc7XEL+qK4iQHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3862cc462c269f1b40354145b8e1ff1b4b785efbeb6aa61ecb7b4756fa90a21","last_reissued_at":"2026-07-05T06:34:07.641426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:07.641426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Molecular Properties from Natural Language with Multimodal Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Andrew Gaut, David L\\\"udeke, Jeff He, Kateryna Pistunova, Romain Lacombe","submitted_at":"2023-07-22T10:32:58Z","abstract_excerpt":"Deep learning in computational biochemistry has traditionally focused on molecular graphs neural representations; however, recent advances in language models highlight how much scientific knowledge is encoded in text. To bridge these two modalities, we investigate how molecular property information can be transferred from natural language to graph representations. We study property prediction performance gains after using contrastive learning to align neural graph representations with representations of textual descriptions of their characteristics. We implement neural relevance scoring strate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12996","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/2307.12996/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":"2307.12996","created_at":"2026-07-05T06:34:07.641483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12996v1","created_at":"2026-07-05T06:34:07.641483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12996","created_at":"2026-07-05T06:34:07.641483+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ODCZRDCYJU7","created_at":"2026-07-05T06:34:07.641483+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ODCZRDCYJU7DNAD","created_at":"2026-07-05T06:34:07.641483+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ODCZRDC","created_at":"2026-07-05T06:34:07.641483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22077","citing_title":"Morphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G","json":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G.json","graph_json":"https://pith.science/api/pith-number/6ODCZRDCYJU7DNADKQKFXDQ76G/graph.json","events_json":"https://pith.science/api/pith-number/6ODCZRDCYJU7DNADKQKFXDQ76G/events.json","paper":"https://pith.science/paper/6ODCZRDC"},"agent_actions":{"view_html":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G","download_json":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G.json","view_paper":"https://pith.science/paper/6ODCZRDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12996&json=true","fetch_graph":"https://pith.science/api/pith-number/6ODCZRDCYJU7DNADKQKFXDQ76G/graph.json","fetch_events":"https://pith.science/api/pith-number/6ODCZRDCYJU7DNADKQKFXDQ76G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G/action/storage_attestation","attest_author":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G/action/author_attestation","sign_citation":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G/action/citation_signature","submit_replication":"https://pith.science/pith/6ODCZRDCYJU7DNADKQKFXDQ76G/action/replication_record"}},"created_at":"2026-07-05T06:34:07.641483+00:00","updated_at":"2026-07-05T06:34:07.641483+00:00"}