{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VBDXDTAKD2DJZLDZ4UKHZTO5E5","short_pith_number":"pith:VBDXDTAK","schema_version":"1.0","canonical_sha256":"a84771cc0a1e869cac79e5147ccddd277b21f0f890ea863e28fabee921366f1d","source":{"kind":"arxiv","id":"2405.15389","version":3},"attestation_state":"computed","paper":{"title":"Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fred A. Hamprecht, Gerrit Gerhartz, Peter Lippmann, Roman Remme","submitted_at":"2024-05-24T09:41:06Z","abstract_excerpt":"In numerous applications of geometric deep learning, the studied systems exhibit spatial symmetries and it is desirable to enforce these. For the symmetry of global rotations and reflections, this means that the model should be equivariant with respect to the transformations that form the group of $\\mathrm O(d)$. While many approaches for equivariant message passing require specialized architectures, including non-standard normalization layers or non-linearities, we here present a framework based on local reference frames (\"local canonicalization\") which can be integrated with any architecture"},"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":"2405.15389","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T09:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"e4dbb137e482b686f7fa0da2ab0f5b496c28fe2132f03f261eef22c65eaf6085","abstract_canon_sha256":"bfdc47207af47ff3fb00723c8a73a25755c0abfaa055e8512df049e4726d5c0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:53.809863Z","signature_b64":"uzITGVDh5O474ddKvgY8PAghBaEdEEzygCPq4sD0/l1DLwPzCgYfWbZXDxE1GjFaF/z/gmy6ro7Yy8B1Ya5WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a84771cc0a1e869cac79e5147ccddd277b21f0f890ea863e28fabee921366f1d","last_reissued_at":"2026-07-05T10:24:53.809213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:53.809213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fred A. Hamprecht, Gerrit Gerhartz, Peter Lippmann, Roman Remme","submitted_at":"2024-05-24T09:41:06Z","abstract_excerpt":"In numerous applications of geometric deep learning, the studied systems exhibit spatial symmetries and it is desirable to enforce these. For the symmetry of global rotations and reflections, this means that the model should be equivariant with respect to the transformations that form the group of $\\mathrm O(d)$. While many approaches for equivariant message passing require specialized architectures, including non-standard normalization layers or non-linearities, we here present a framework based on local reference frames (\"local canonicalization\") which can be integrated with any architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15389","kind":"arxiv","version":3},"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/2405.15389/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":"2405.15389","created_at":"2026-07-05T10:24:53.809284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15389v3","created_at":"2026-07-05T10:24:53.809284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15389","created_at":"2026-07-05T10:24:53.809284+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBDXDTAKD2DJ","created_at":"2026-07-05T10:24:53.809284+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBDXDTAKD2DJZLDZ","created_at":"2026-07-05T10:24:53.809284+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBDXDTAK","created_at":"2026-07-05T10:24:53.809284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09647","citing_title":"Ab initio parametrization of distributed polarizable force fields","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16891","citing_title":"Tensor Channel Equivariant Graph Neural Networks for Molecular Polarizability Prediction","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5","json":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5.json","graph_json":"https://pith.science/api/pith-number/VBDXDTAKD2DJZLDZ4UKHZTO5E5/graph.json","events_json":"https://pith.science/api/pith-number/VBDXDTAKD2DJZLDZ4UKHZTO5E5/events.json","paper":"https://pith.science/paper/VBDXDTAK"},"agent_actions":{"view_html":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5","download_json":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5.json","view_paper":"https://pith.science/paper/VBDXDTAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15389&json=true","fetch_graph":"https://pith.science/api/pith-number/VBDXDTAKD2DJZLDZ4UKHZTO5E5/graph.json","fetch_events":"https://pith.science/api/pith-number/VBDXDTAKD2DJZLDZ4UKHZTO5E5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5/action/storage_attestation","attest_author":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5/action/author_attestation","sign_citation":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5/action/citation_signature","submit_replication":"https://pith.science/pith/VBDXDTAKD2DJZLDZ4UKHZTO5E5/action/replication_record"}},"created_at":"2026-07-05T10:24:53.809284+00:00","updated_at":"2026-07-05T10:24:53.809284+00:00"}