{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X43WL3DM3SGCW4VVYT4HCRGNBA","short_pith_number":"pith:X43WL3DM","schema_version":"1.0","canonical_sha256":"bf3765ec6cdc8c2b72b5c4f87144cd0811f663e64e0840976b90bbbd41c0dd4f","source":{"kind":"arxiv","id":"2507.09785","version":1},"attestation_state":"computed","paper":{"title":"Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Allan dos Santos Costa, Danny Reidenbach, Emine Kucukbenli, Franco Pellegrini, Guoqing Zhou, Karsten Kreis, Mario Geiger, Tomas Geffner, Zhonglin Cao","submitted_at":"2025-07-13T20:48:21Z","abstract_excerpt":"Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matching and propose two mechanisms for accelerating training and inference of generative models for 3D molecular conformer generation. For fast training, we introduce the SO(3)-Averaged Flow training objective, which leads to faster convergence to better generation quality compared to "},"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":"2507.09785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T20:48:21Z","cross_cats_sorted":["physics.chem-ph"],"title_canon_sha256":"1030dfb08717fb83fe12d161ed1c5261f06dbf445bd0370d846b89f85f0c2348","abstract_canon_sha256":"11133ea54d4076be20a9cafe8df0521fd8fcc3021be5acb46164df326e29bff7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:39.796375Z","signature_b64":"Ax24TNwhzYp0YryNWdnTWoz0hxsQw/XNzoa4GSVCePonFlHexrx1nj2viWh6wJYcIR1qkM1NTNqiWtjO7mJ4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3765ec6cdc8c2b72b5c4f87144cd0811f663e64e0840976b90bbbd41c0dd4f","last_reissued_at":"2026-07-05T11:36:39.795750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:39.795750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Allan dos Santos Costa, Danny Reidenbach, Emine Kucukbenli, Franco Pellegrini, Guoqing Zhou, Karsten Kreis, Mario Geiger, Tomas Geffner, Zhonglin Cao","submitted_at":"2025-07-13T20:48:21Z","abstract_excerpt":"Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matching and propose two mechanisms for accelerating training and inference of generative models for 3D molecular conformer generation. For fast training, we introduce the SO(3)-Averaged Flow training objective, which leads to faster convergence to better generation quality compared to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09785","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/2507.09785/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":"2507.09785","created_at":"2026-07-05T11:36:39.795904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09785v1","created_at":"2026-07-05T11:36:39.795904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09785","created_at":"2026-07-05T11:36:39.795904+00:00"},{"alias_kind":"pith_short_12","alias_value":"X43WL3DM3SGC","created_at":"2026-07-05T11:36:39.795904+00:00"},{"alias_kind":"pith_short_16","alias_value":"X43WL3DM3SGCW4VV","created_at":"2026-07-05T11:36:39.795904+00:00"},{"alias_kind":"pith_short_8","alias_value":"X43WL3DM","created_at":"2026-07-05T11:36:39.795904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25577","citing_title":"Geometric Flow Matching for Molecular Conformation Generation via Manifold Decomposition","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22597","citing_title":"Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA","json":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA.json","graph_json":"https://pith.science/api/pith-number/X43WL3DM3SGCW4VVYT4HCRGNBA/graph.json","events_json":"https://pith.science/api/pith-number/X43WL3DM3SGCW4VVYT4HCRGNBA/events.json","paper":"https://pith.science/paper/X43WL3DM"},"agent_actions":{"view_html":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA","download_json":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA.json","view_paper":"https://pith.science/paper/X43WL3DM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09785&json=true","fetch_graph":"https://pith.science/api/pith-number/X43WL3DM3SGCW4VVYT4HCRGNBA/graph.json","fetch_events":"https://pith.science/api/pith-number/X43WL3DM3SGCW4VVYT4HCRGNBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA/action/storage_attestation","attest_author":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA/action/author_attestation","sign_citation":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA/action/citation_signature","submit_replication":"https://pith.science/pith/X43WL3DM3SGCW4VVYT4HCRGNBA/action/replication_record"}},"created_at":"2026-07-05T11:36:39.795904+00:00","updated_at":"2026-07-05T11:36:39.795904+00:00"}