{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C43V5IF5Z6KMCOCDXYN7M3EXY2","short_pith_number":"pith:C43V5IF5","schema_version":"1.0","canonical_sha256":"17375ea0bdcf94c13843be1bf66c97c6b8ae2474df61c3ce100545e3ef70ae2f","source":{"kind":"arxiv","id":"2405.15252","version":2},"attestation_state":"computed","paper":{"title":"Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haokai Hong, Kay Chen Tan, Wanyu Lin","submitted_at":"2024-05-24T06:22:01Z","abstract_excerpt":"This paper proposes a new 3D molecule generation framework, called GOAT, for fast and effective 3D molecule generation based on the flow-matching optimal transport objective. Specifically, we formulate a geometric transport formula for measuring the cost of mapping multi-modal features (e.g., continuous atom coordinates and categorical atom types) between a base distribution and a target data distribution. Our formula is solved within a joint, equivariant, and smooth representation space. This is achieved by transforming the multi-modal features into a continuous latent space with equivariant "},"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":"2405.15252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T06:22:01Z","cross_cats_sorted":[],"title_canon_sha256":"c0a9a18bc59b4b4f4a1fc6905e30888c551518535701880f13333bbb9c261bc6","abstract_canon_sha256":"e6857977f7534b9c2cc07c0a0e7c4570f5fb15149f31aedea921722bdfd54b66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:59.931070Z","signature_b64":"Y1FRWRUKzwTToaE3CjY4U+l0o+du+u8ng6ia7zcZelZZs6HGYQdTWlnFS9Wvq/uD13UZF0dnPf+1tYCIwEkCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17375ea0bdcf94c13843be1bf66c97c6b8ae2474df61c3ce100545e3ef70ae2f","last_reissued_at":"2026-07-05T10:21:59.930564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:59.930564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haokai Hong, Kay Chen Tan, Wanyu Lin","submitted_at":"2024-05-24T06:22:01Z","abstract_excerpt":"This paper proposes a new 3D molecule generation framework, called GOAT, for fast and effective 3D molecule generation based on the flow-matching optimal transport objective. Specifically, we formulate a geometric transport formula for measuring the cost of mapping multi-modal features (e.g., continuous atom coordinates and categorical atom types) between a base distribution and a target data distribution. Our formula is solved within a joint, equivariant, and smooth representation space. This is achieved by transforming the multi-modal features into a continuous latent space with equivariant "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15252","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/2405.15252/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":"2405.15252","created_at":"2026-07-05T10:21:59.930631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15252v2","created_at":"2026-07-05T10:21:59.930631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15252","created_at":"2026-07-05T10:21:59.930631+00:00"},{"alias_kind":"pith_short_12","alias_value":"C43V5IF5Z6KM","created_at":"2026-07-05T10:21:59.930631+00:00"},{"alias_kind":"pith_short_16","alias_value":"C43V5IF5Z6KMCOCD","created_at":"2026-07-05T10:21:59.930631+00:00"},{"alias_kind":"pith_short_8","alias_value":"C43V5IF5","created_at":"2026-07-05T10:21:59.930631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07020","citing_title":"FlashMol: High-Quality Molecule Generation in as Few as Four Steps","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07693","citing_title":"Toward Better Geometric Representations for Molecule Generative Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2","json":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2.json","graph_json":"https://pith.science/api/pith-number/C43V5IF5Z6KMCOCDXYN7M3EXY2/graph.json","events_json":"https://pith.science/api/pith-number/C43V5IF5Z6KMCOCDXYN7M3EXY2/events.json","paper":"https://pith.science/paper/C43V5IF5"},"agent_actions":{"view_html":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2","download_json":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2.json","view_paper":"https://pith.science/paper/C43V5IF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15252&json=true","fetch_graph":"https://pith.science/api/pith-number/C43V5IF5Z6KMCOCDXYN7M3EXY2/graph.json","fetch_events":"https://pith.science/api/pith-number/C43V5IF5Z6KMCOCDXYN7M3EXY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2/action/storage_attestation","attest_author":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2/action/author_attestation","sign_citation":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2/action/citation_signature","submit_replication":"https://pith.science/pith/C43V5IF5Z6KMCOCDXYN7M3EXY2/action/replication_record"}},"created_at":"2026-07-05T10:21:59.930631+00:00","updated_at":"2026-07-05T10:21:59.930631+00:00"}