{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SPJFC35IT3SZMZEV7BYGGRT3S6","short_pith_number":"pith:SPJFC35I","schema_version":"1.0","canonical_sha256":"93d2516fa89ee5966495f87063467b97b6a46bc2eaa0e002fe27dbe477bd40d5","source":{"kind":"arxiv","id":"2309.17296","version":2},"attestation_state":"computed","paper":{"title":"Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Djork-Arn\\'e Clevert, Frank No\\'e, Julian Cremer, Kristof Sch\\\"utt, Tuan Le","submitted_at":"2023-09-29T14:53:05Z","abstract_excerpt":"Deep generative diffusion models are a promising avenue for 3D de novo molecular design in materials science and drug discovery. However, their utility is still limited by suboptimal performance on large molecular structures and limited training data. To address this gap, we explore the design space of E(3)-equivariant diffusion models, focusing on previously unexplored areas. Our extensive comparative analysis evaluates the interplay between continuous and discrete state spaces. From this investigation, we present the EQGAT-diff model, which consistently outperforms established models for 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":"2309.17296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T14:53:05Z","cross_cats_sorted":[],"title_canon_sha256":"522274d672f14d9d27c9f0903f76e5009374dd62ace7bf26bb5f982fceda712b","abstract_canon_sha256":"a9115de76da65500ebaa6f7ca02aef86c3daf76c475740fafc2809f9e0949da8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:00.642912Z","signature_b64":"btbTKbUhAAWOE4xFz3quRBx7YyqvRpYueWG+I2qc4bkVgDuNrtT6HCRnKJ8QKsC2qlg3jIxp9/mW7ANDW7hjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93d2516fa89ee5966495f87063467b97b6a46bc2eaa0e002fe27dbe477bd40d5","last_reissued_at":"2026-07-05T07:16:00.642291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:00.642291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Djork-Arn\\'e Clevert, Frank No\\'e, Julian Cremer, Kristof Sch\\\"utt, Tuan Le","submitted_at":"2023-09-29T14:53:05Z","abstract_excerpt":"Deep generative diffusion models are a promising avenue for 3D de novo molecular design in materials science and drug discovery. However, their utility is still limited by suboptimal performance on large molecular structures and limited training data. To address this gap, we explore the design space of E(3)-equivariant diffusion models, focusing on previously unexplored areas. Our extensive comparative analysis evaluates the interplay between continuous and discrete state spaces. From this investigation, we present the EQGAT-diff model, which consistently outperforms established models for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17296","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/2309.17296/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":"2309.17296","created_at":"2026-07-05T07:16:00.642381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17296v2","created_at":"2026-07-05T07:16:00.642381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17296","created_at":"2026-07-05T07:16:00.642381+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPJFC35IT3SZ","created_at":"2026-07-05T07:16:00.642381+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPJFC35IT3SZMZEV","created_at":"2026-07-05T07:16:00.642381+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPJFC35I","created_at":"2026-07-05T07:16:00.642381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07239","citing_title":"Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07693","citing_title":"Toward Better Geometric Representations for Molecule Generative Models","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6","json":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6.json","graph_json":"https://pith.science/api/pith-number/SPJFC35IT3SZMZEV7BYGGRT3S6/graph.json","events_json":"https://pith.science/api/pith-number/SPJFC35IT3SZMZEV7BYGGRT3S6/events.json","paper":"https://pith.science/paper/SPJFC35I"},"agent_actions":{"view_html":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6","download_json":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6.json","view_paper":"https://pith.science/paper/SPJFC35I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17296&json=true","fetch_graph":"https://pith.science/api/pith-number/SPJFC35IT3SZMZEV7BYGGRT3S6/graph.json","fetch_events":"https://pith.science/api/pith-number/SPJFC35IT3SZMZEV7BYGGRT3S6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6/action/storage_attestation","attest_author":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6/action/author_attestation","sign_citation":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6/action/citation_signature","submit_replication":"https://pith.science/pith/SPJFC35IT3SZMZEV7BYGGRT3S6/action/replication_record"}},"created_at":"2026-07-05T07:16:00.642381+00:00","updated_at":"2026-07-05T07:16:00.642381+00:00"}