{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:45YFDNOZC3IDWG5DUSX2M2ZJT6","short_pith_number":"pith:45YFDNOZ","schema_version":"1.0","canonical_sha256":"e77051b5d916d03b1ba3a4afa66b299fa66794ed01da32f392382d72a02b76b3","source":{"kind":"arxiv","id":"2403.07179","version":2},"attestation_state":"computed","paper":{"title":"3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Huaisheng Zhu, Teng Xiao, Vasant G Honavar","submitted_at":"2024-03-11T21:44:54Z","abstract_excerpt":"Generating molecular structures with desired properties is a critical task with broad applications in drug discovery and materials design. We propose 3M-Diffusion, a novel multi-modal molecular graph generation method, to generate diverse, ideally novel molecular structures with desired properties. 3M-Diffusion encodes molecular graphs into a graph latent space which it then aligns with the text space learned by encoder-based LLMs from textual descriptions. It then reconstructs the molecular structure and atomic attributes based on the given text descriptions using the molecule decoder. It the"},"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":"2403.07179","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T21:44:54Z","cross_cats_sorted":["cs.CL","q-bio.BM"],"title_canon_sha256":"efc415437b6aba049e3a9ce2a17b5d2984646bc5d6c700e8217d9025e9677452","abstract_canon_sha256":"f84a05c04a35ae836c1efd0be6f431e843e132a7ccd3d32d3d618e1d7c1031e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:54.020378Z","signature_b64":"EMFY3X/hps98BRNYkriJZiW4efEs2HOncV8dLLsB+Iue2BI2ZYqlyibvXO3ImXmiwdcb3IkPRSSHcRtocETSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e77051b5d916d03b1ba3a4afa66b299fa66794ed01da32f392382d72a02b76b3","last_reissued_at":"2026-07-05T09:14:54.019913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:54.019913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Huaisheng Zhu, Teng Xiao, Vasant G Honavar","submitted_at":"2024-03-11T21:44:54Z","abstract_excerpt":"Generating molecular structures with desired properties is a critical task with broad applications in drug discovery and materials design. We propose 3M-Diffusion, a novel multi-modal molecular graph generation method, to generate diverse, ideally novel molecular structures with desired properties. 3M-Diffusion encodes molecular graphs into a graph latent space which it then aligns with the text space learned by encoder-based LLMs from textual descriptions. It then reconstructs the molecular structure and atomic attributes based on the given text descriptions using the molecule decoder. It the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07179","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/2403.07179/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":"2403.07179","created_at":"2026-07-05T09:14:54.019969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07179v2","created_at":"2026-07-05T09:14:54.019969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07179","created_at":"2026-07-05T09:14:54.019969+00:00"},{"alias_kind":"pith_short_12","alias_value":"45YFDNOZC3ID","created_at":"2026-07-05T09:14:54.019969+00:00"},{"alias_kind":"pith_short_16","alias_value":"45YFDNOZC3IDWG5D","created_at":"2026-07-05T09:14:54.019969+00:00"},{"alias_kind":"pith_short_8","alias_value":"45YFDNOZ","created_at":"2026-07-05T09:14:54.019969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10821","citing_title":"GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6","json":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6.json","graph_json":"https://pith.science/api/pith-number/45YFDNOZC3IDWG5DUSX2M2ZJT6/graph.json","events_json":"https://pith.science/api/pith-number/45YFDNOZC3IDWG5DUSX2M2ZJT6/events.json","paper":"https://pith.science/paper/45YFDNOZ"},"agent_actions":{"view_html":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6","download_json":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6.json","view_paper":"https://pith.science/paper/45YFDNOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07179&json=true","fetch_graph":"https://pith.science/api/pith-number/45YFDNOZC3IDWG5DUSX2M2ZJT6/graph.json","fetch_events":"https://pith.science/api/pith-number/45YFDNOZC3IDWG5DUSX2M2ZJT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6/action/storage_attestation","attest_author":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6/action/author_attestation","sign_citation":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6/action/citation_signature","submit_replication":"https://pith.science/pith/45YFDNOZC3IDWG5DUSX2M2ZJT6/action/replication_record"}},"created_at":"2026-07-05T09:14:54.019969+00:00","updated_at":"2026-07-05T09:14:54.019969+00:00"}