{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NIPDYBT4VZAKQRM322KG2UCYPQ","short_pith_number":"pith:NIPDYBT4","schema_version":"1.0","canonical_sha256":"6a1e3c067cae40a8459bd6946d50587c099a4c53390de385f89a8d57c9a50eb0","source":{"kind":"arxiv","id":"2505.00518","version":1},"attestation_state":"computed","paper":{"title":"An evaluation of unconditional 3D molecular generation methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"physics.chem-ph","authors_text":"Charlotte M. Deane, Garrett M. Morris, Martin Buttenschoen, Yael Ziv","submitted_at":"2025-05-01T13:40:10Z","abstract_excerpt":"Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in \\emph{de novo} drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high-performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, and SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has a success rate of 87% in generating valid, unique, and n"},"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":"2505.00518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2025-05-01T13:40:10Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"3feaa260402978ea3eef00a12738cb49a1f33c2ce0c3fbb71af256adb41c01c8","abstract_canon_sha256":"8480c72198d9c825b6454bf02f047c06c474dd4bb374b581179dd4f35387f920"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:14.883246Z","signature_b64":"+uPcz0DChoeNkBytRjzOGLckBJHsLSGVshQhJlPLD98oGZiiXlWLSQ4CYW5dWGWhkrLZs659plluPb/wtfpkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a1e3c067cae40a8459bd6946d50587c099a4c53390de385f89a8d57c9a50eb0","last_reissued_at":"2026-07-05T10:57:14.882747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:14.882747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An evaluation of unconditional 3D molecular generation methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"physics.chem-ph","authors_text":"Charlotte M. Deane, Garrett M. Morris, Martin Buttenschoen, Yael Ziv","submitted_at":"2025-05-01T13:40:10Z","abstract_excerpt":"Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in \\emph{de novo} drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high-performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, and SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has a success rate of 87% in generating valid, unique, and n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00518","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/2505.00518/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":"2505.00518","created_at":"2026-07-05T10:57:14.882805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00518v1","created_at":"2026-07-05T10:57:14.882805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00518","created_at":"2026-07-05T10:57:14.882805+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIPDYBT4VZAK","created_at":"2026-07-05T10:57:14.882805+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIPDYBT4VZAKQRM3","created_at":"2026-07-05T10:57:14.882805+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIPDYBT4","created_at":"2026-07-05T10:57:14.882805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12629","citing_title":"FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ","json":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ.json","graph_json":"https://pith.science/api/pith-number/NIPDYBT4VZAKQRM322KG2UCYPQ/graph.json","events_json":"https://pith.science/api/pith-number/NIPDYBT4VZAKQRM322KG2UCYPQ/events.json","paper":"https://pith.science/paper/NIPDYBT4"},"agent_actions":{"view_html":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ","download_json":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ.json","view_paper":"https://pith.science/paper/NIPDYBT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00518&json=true","fetch_graph":"https://pith.science/api/pith-number/NIPDYBT4VZAKQRM322KG2UCYPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NIPDYBT4VZAKQRM322KG2UCYPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ/action/storage_attestation","attest_author":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ/action/author_attestation","sign_citation":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ/action/citation_signature","submit_replication":"https://pith.science/pith/NIPDYBT4VZAKQRM322KG2UCYPQ/action/replication_record"}},"created_at":"2026-07-05T10:57:14.882805+00:00","updated_at":"2026-07-05T10:57:14.882805+00:00"}