{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYGOIZZ2E7WAKSEYS4GKXLJRFH","short_pith_number":"pith:DYGOIZZ2","schema_version":"1.0","canonical_sha256":"1e0ce4673a27ec054898970cabad3129c9218fa3d798b8bae41ddd836d147667","source":{"kind":"arxiv","id":"2408.09896","version":2},"attestation_state":"computed","paper":{"title":"Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Chang Ma, Haiteng Zhao, Yuran Xiang, Zhi-Hong Deng","submitted_at":"2024-08-19T11:09:15Z","abstract_excerpt":"Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current methods to use molecular sequences with pre-trained large language models. In response to this challenge, we propose a novel framework, named $\\textbf{UTGDiff (Unified Text-Graph Diffusion Model)}$, which utilizes language models for discrete graph diffusion to generate molecular graphs from instructions. UTGDiff features a unified text-graph transformer as the denoising network, d"},"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":"2408.09896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T11:09:15Z","cross_cats_sorted":["physics.chem-ph","q-bio.BM"],"title_canon_sha256":"6b0401a1714cb829972f6741c3b1232dabe102660c123d423439baab3ffa5f7b","abstract_canon_sha256":"2c85eac1a1507017fcd638e2ff310b4eb8a20490bdb3ea89bfa6fcc431f3404d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:06.920145Z","signature_b64":"I5niqm+HeUe1wROOzEO7Du9iPAzwQk9eTyqrJJL8dFI87SCB2Vlc7wSWHQZzy/UStyN8tGXOtwWaG2wFjwZCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e0ce4673a27ec054898970cabad3129c9218fa3d798b8bae41ddd836d147667","last_reissued_at":"2026-07-05T11:59:06.919699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:06.919699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Chang Ma, Haiteng Zhao, Yuran Xiang, Zhi-Hong Deng","submitted_at":"2024-08-19T11:09:15Z","abstract_excerpt":"Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current methods to use molecular sequences with pre-trained large language models. In response to this challenge, we propose a novel framework, named $\\textbf{UTGDiff (Unified Text-Graph Diffusion Model)}$, which utilizes language models for discrete graph diffusion to generate molecular graphs from instructions. UTGDiff features a unified text-graph transformer as the denoising network, d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09896","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/2408.09896/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":"2408.09896","created_at":"2026-07-05T11:59:06.919751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09896v2","created_at":"2026-07-05T11:59:06.919751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09896","created_at":"2026-07-05T11:59:06.919751+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYGOIZZ2E7WA","created_at":"2026-07-05T11:59:06.919751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYGOIZZ2E7WAKSEY","created_at":"2026-07-05T11:59:06.919751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYGOIZZ2","created_at":"2026-07-05T11:59:06.919751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24089","citing_title":"BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH","json":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH.json","graph_json":"https://pith.science/api/pith-number/DYGOIZZ2E7WAKSEYS4GKXLJRFH/graph.json","events_json":"https://pith.science/api/pith-number/DYGOIZZ2E7WAKSEYS4GKXLJRFH/events.json","paper":"https://pith.science/paper/DYGOIZZ2"},"agent_actions":{"view_html":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH","download_json":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH.json","view_paper":"https://pith.science/paper/DYGOIZZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09896&json=true","fetch_graph":"https://pith.science/api/pith-number/DYGOIZZ2E7WAKSEYS4GKXLJRFH/graph.json","fetch_events":"https://pith.science/api/pith-number/DYGOIZZ2E7WAKSEYS4GKXLJRFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH/action/storage_attestation","attest_author":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH/action/author_attestation","sign_citation":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH/action/citation_signature","submit_replication":"https://pith.science/pith/DYGOIZZ2E7WAKSEYS4GKXLJRFH/action/replication_record"}},"created_at":"2026-07-05T11:59:06.919751+00:00","updated_at":"2026-07-05T11:59:06.919751+00:00"}