{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MQPMPZUKTKYZ4I63AZCGFPWRRI","short_pith_number":"pith:MQPMPZUK","schema_version":"1.0","canonical_sha256":"641ec7e68a9ab19e23db064462bed18a11da7271769535fdbbef9f29bdf4eea0","source":{"kind":"arxiv","id":"2506.00009","version":1},"attestation_state":"computed","paper":{"title":"MolTextNet: A Two-Million Molecule-Text Dataset for Multimodal Molecular Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Eric Inae, Gang Liu, Meng Jiang, Yihan Zhu","submitted_at":"2025-05-15T19:50:11Z","abstract_excerpt":"Small molecules are essential to drug discovery, and graph-language models hold promise for learning molecular properties and functions from text. However, existing molecule-text datasets are limited in scale and informativeness, restricting the training of generalizable multimodal models. We present MolTextNet, a dataset of 2.5 million high-quality molecule-text pairs designed to overcome these limitations. To construct it, we propose a synthetic text generation pipeline that integrates structural features, computed properties, bioactivity data, and synthetic complexity. Using GPT-4o-mini, we"},"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":"2506.00009","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-05-15T19:50:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10d64265add171469675fb09397e780c37f7c232604b146861f6aa8da68fb106","abstract_canon_sha256":"3a46f097e9d6227735e921e531307ba5af630e61c318010896d4ee38c64276ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:58.522462Z","signature_b64":"7Hysw0nN+FkvqnCzB4SpA4+YCmtVPiZc/0JQRf24HYODCagea0b6VFfJLXK9nO5FY7nnjXO0PHyqjxSVksXHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641ec7e68a9ab19e23db064462bed18a11da7271769535fdbbef9f29bdf4eea0","last_reissued_at":"2026-07-05T11:12:58.521904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:58.521904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolTextNet: A Two-Million Molecule-Text Dataset for Multimodal Molecular Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Eric Inae, Gang Liu, Meng Jiang, Yihan Zhu","submitted_at":"2025-05-15T19:50:11Z","abstract_excerpt":"Small molecules are essential to drug discovery, and graph-language models hold promise for learning molecular properties and functions from text. However, existing molecule-text datasets are limited in scale and informativeness, restricting the training of generalizable multimodal models. We present MolTextNet, a dataset of 2.5 million high-quality molecule-text pairs designed to overcome these limitations. To construct it, we propose a synthetic text generation pipeline that integrates structural features, computed properties, bioactivity data, and synthetic complexity. Using GPT-4o-mini, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00009","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/2506.00009/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":"2506.00009","created_at":"2026-07-05T11:12:58.521975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00009v1","created_at":"2026-07-05T11:12:58.521975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00009","created_at":"2026-07-05T11:12:58.521975+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQPMPZUKTKYZ","created_at":"2026-07-05T11:12:58.521975+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQPMPZUKTKYZ4I63","created_at":"2026-07-05T11:12:58.521975+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQPMPZUK","created_at":"2026-07-05T11:12:58.521975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22138","citing_title":"BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02346","citing_title":"DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27351","citing_title":"Heterogeneous Scientific Foundation Model Collaboration","ref_index":138,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI","json":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI.json","graph_json":"https://pith.science/api/pith-number/MQPMPZUKTKYZ4I63AZCGFPWRRI/graph.json","events_json":"https://pith.science/api/pith-number/MQPMPZUKTKYZ4I63AZCGFPWRRI/events.json","paper":"https://pith.science/paper/MQPMPZUK"},"agent_actions":{"view_html":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI","download_json":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI.json","view_paper":"https://pith.science/paper/MQPMPZUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00009&json=true","fetch_graph":"https://pith.science/api/pith-number/MQPMPZUKTKYZ4I63AZCGFPWRRI/graph.json","fetch_events":"https://pith.science/api/pith-number/MQPMPZUKTKYZ4I63AZCGFPWRRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI/action/storage_attestation","attest_author":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI/action/author_attestation","sign_citation":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI/action/citation_signature","submit_replication":"https://pith.science/pith/MQPMPZUKTKYZ4I63AZCGFPWRRI/action/replication_record"}},"created_at":"2026-07-05T11:12:58.521975+00:00","updated_at":"2026-07-05T11:12:58.521975+00:00"}