{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6APGZEPJURWCSCYWEE22DPWX2S","short_pith_number":"pith:6APGZEPJ","schema_version":"1.0","canonical_sha256":"f01e6c91e9a46c290b162135a1bed7d4a853551ad778f966d8d2adb019dfb785","source":{"kind":"arxiv","id":"2506.10186","version":2},"attestation_state":"computed","paper":{"title":"Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Thomas Hofmann, Yuhui Ding","submitted_at":"2025-06-11T21:23:56Z","abstract_excerpt":"Equivariant diffusion models have achieved impressive performance in 3D molecule generation. These models incorporate Euclidean symmetries of 3D molecules by utilizing an SE(3)-equivariant denoising network. However, specialized equivariant architectures limit the scalability and efficiency of diffusion models. In this paper, we propose an approach that relaxes such equivariance constraints. Specifically, our approach learns a sample-dependent SO(3) transformation for each molecule to construct an aligned latent space. A non-equivariant diffusion model is then trained over the aligned represen"},"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":"2506.10186","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T21:23:56Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"9236d6f41842667af293552e1de44f7a3c6976b47f2638c1d1030630d39aa9f5","abstract_canon_sha256":"1cdb57336562bdd396c8eb594e3484d9e65771b0d72947a7204796f18333c341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:13.040608Z","signature_b64":"Gz1y6MQa/RhLv9LCraL46MdoSGNIH0WBx3nJ7jECF8+Vj+4h/HAHfBURrvIq0Tz4HOuRf7xH1HW7kIk9HhnABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01e6c91e9a46c290b162135a1bed7d4a853551ad778f966d8d2adb019dfb785","last_reissued_at":"2026-07-05T11:29:13.039757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:13.039757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Thomas Hofmann, Yuhui Ding","submitted_at":"2025-06-11T21:23:56Z","abstract_excerpt":"Equivariant diffusion models have achieved impressive performance in 3D molecule generation. These models incorporate Euclidean symmetries of 3D molecules by utilizing an SE(3)-equivariant denoising network. However, specialized equivariant architectures limit the scalability and efficiency of diffusion models. In this paper, we propose an approach that relaxes such equivariance constraints. Specifically, our approach learns a sample-dependent SO(3) transformation for each molecule to construct an aligned latent space. A non-equivariant diffusion model is then trained over the aligned represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10186","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/2506.10186/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":"2506.10186","created_at":"2026-07-05T11:29:13.039863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10186v2","created_at":"2026-07-05T11:29:13.039863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10186","created_at":"2026-07-05T11:29:13.039863+00:00"},{"alias_kind":"pith_short_12","alias_value":"6APGZEPJURWC","created_at":"2026-07-05T11:29:13.039863+00:00"},{"alias_kind":"pith_short_16","alias_value":"6APGZEPJURWCSCYW","created_at":"2026-07-05T11:29:13.039863+00:00"},{"alias_kind":"pith_short_8","alias_value":"6APGZEPJ","created_at":"2026-07-05T11:29:13.039863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01595","citing_title":"Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S","json":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S.json","graph_json":"https://pith.science/api/pith-number/6APGZEPJURWCSCYWEE22DPWX2S/graph.json","events_json":"https://pith.science/api/pith-number/6APGZEPJURWCSCYWEE22DPWX2S/events.json","paper":"https://pith.science/paper/6APGZEPJ"},"agent_actions":{"view_html":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S","download_json":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S.json","view_paper":"https://pith.science/paper/6APGZEPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10186&json=true","fetch_graph":"https://pith.science/api/pith-number/6APGZEPJURWCSCYWEE22DPWX2S/graph.json","fetch_events":"https://pith.science/api/pith-number/6APGZEPJURWCSCYWEE22DPWX2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S/action/storage_attestation","attest_author":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S/action/author_attestation","sign_citation":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S/action/citation_signature","submit_replication":"https://pith.science/pith/6APGZEPJURWCSCYWEE22DPWX2S/action/replication_record"}},"created_at":"2026-07-05T11:29:13.039863+00:00","updated_at":"2026-07-05T11:29:13.039863+00:00"}