{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PTA3JIE7KXAQDRVFPQDL2ZSJUU","short_pith_number":"pith:PTA3JIE7","schema_version":"1.0","canonical_sha256":"7cc1b4a09f55c101c6a57c06bd6649a51a724d58c4ad35c6b4a432bc16814f18","source":{"kind":"arxiv","id":"2201.11969","version":4},"attestation_state":"computed","paper":{"title":"Approximately Equivariant Networks for Imperfectly Symmetric Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Robin Walters, Rose Yu, Rui Wang","submitted_at":"2022-01-28T07:31:28Z","abstract_excerpt":"Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling. Methods such as CNNs or equivariant neural networks use weight tying to enforce symmetries such as shift invariance or rotational equivariance. However, despite the fact that physical laws obey many symmetries, real-world dynamical data rarely conforms to strict mathematical symmetry either due to noisy or incomplete data or to symmetry breaking features in the underlying dynamical system. We explore approximatel"},"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":"2201.11969","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T07:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"916e1d47af8ec029dbbae1b63e77ffd6c9dfa6b2c57cdb6621718caabd4599c6","abstract_canon_sha256":"be6568c7906d0199b42a53afe0d614447019f0a29cd350c3b70b8c57a1b15ae5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:14.361703Z","signature_b64":"a7p3h+Rjg3q/opLris4MkIacnpD8cL85WiVcmJ5cn5nwUDp67W1smbCw5VmlbbJcynlw8rWcq1F4Ic+SoSSMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cc1b4a09f55c101c6a57c06bd6649a51a724d58c4ad35c6b4a432bc16814f18","last_reissued_at":"2026-07-05T04:32:14.361288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:14.361288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximately Equivariant Networks for Imperfectly Symmetric Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Robin Walters, Rose Yu, Rui Wang","submitted_at":"2022-01-28T07:31:28Z","abstract_excerpt":"Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling. Methods such as CNNs or equivariant neural networks use weight tying to enforce symmetries such as shift invariance or rotational equivariance. However, despite the fact that physical laws obey many symmetries, real-world dynamical data rarely conforms to strict mathematical symmetry either due to noisy or incomplete data or to symmetry breaking features in the underlying dynamical system. We explore approximatel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11969","kind":"arxiv","version":4},"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/2201.11969/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":"2201.11969","created_at":"2026-07-05T04:32:14.361353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11969v4","created_at":"2026-07-05T04:32:14.361353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11969","created_at":"2026-07-05T04:32:14.361353+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTA3JIE7KXAQ","created_at":"2026-07-05T04:32:14.361353+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTA3JIE7KXAQDRVF","created_at":"2026-07-05T04:32:14.361353+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTA3JIE7","created_at":"2026-07-05T04:32:14.361353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08244","citing_title":"Algebraic Priors for Approximately Equivariant Networks","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU","json":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU.json","graph_json":"https://pith.science/api/pith-number/PTA3JIE7KXAQDRVFPQDL2ZSJUU/graph.json","events_json":"https://pith.science/api/pith-number/PTA3JIE7KXAQDRVFPQDL2ZSJUU/events.json","paper":"https://pith.science/paper/PTA3JIE7"},"agent_actions":{"view_html":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU","download_json":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU.json","view_paper":"https://pith.science/paper/PTA3JIE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11969&json=true","fetch_graph":"https://pith.science/api/pith-number/PTA3JIE7KXAQDRVFPQDL2ZSJUU/graph.json","fetch_events":"https://pith.science/api/pith-number/PTA3JIE7KXAQDRVFPQDL2ZSJUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU/action/storage_attestation","attest_author":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU/action/author_attestation","sign_citation":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU/action/citation_signature","submit_replication":"https://pith.science/pith/PTA3JIE7KXAQDRVFPQDL2ZSJUU/action/replication_record"}},"created_at":"2026-07-05T04:32:14.361353+00:00","updated_at":"2026-07-05T04:32:14.361353+00:00"}