{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5QVME5O2NKQIIWF2ZZQGG3AEEU","short_pith_number":"pith:5QVME5O2","schema_version":"1.0","canonical_sha256":"ec2ac275da6aa08458bace60636c04251e7d42e81d0b1c364b87f586a96d0cb4","source":{"kind":"arxiv","id":"2305.17592","version":2},"attestation_state":"computed","paper":{"title":"Approximation-Generalization Trade-offs under (Approximate) Group Equivariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mircea Petrache, Shubhendu Trivedi","submitted_at":"2023-05-27T22:53:37Z","abstract_excerpt":"The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural networks have demonstrated impressive performance across various domains and applications such as protein and drug design. A prevalent intuition about such models is that the integration of relevant symmetry results in enhanced generalization. Moreover, it is posited that when the data and/or the model may only exhibit $\\textit{approximate}$ or $\\textit{partial}$ symmetry, 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":"2305.17592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T22:53:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e8481738d83ba1e3b24d1f34a98e30cc77a1951c4d507fc9910ebb76ee0c38cd","abstract_canon_sha256":"d251870431560215a545ff600f724acbcdfc94a542a103de3768147e8645bf96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:40.377795Z","signature_b64":"2jLHExit1mO6FJVEtD3sBdGg1sbo9D9yb6dpRExg551PBSvilu/tws8Mwx33+WV6Rk5SklxPeenhm0iO/KaRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2ac275da6aa08458bace60636c04251e7d42e81d0b1c364b87f586a96d0cb4","last_reissued_at":"2026-07-05T10:50:40.377323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:40.377323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation-Generalization Trade-offs under (Approximate) Group Equivariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mircea Petrache, Shubhendu Trivedi","submitted_at":"2023-05-27T22:53:37Z","abstract_excerpt":"The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural networks have demonstrated impressive performance across various domains and applications such as protein and drug design. A prevalent intuition about such models is that the integration of relevant symmetry results in enhanced generalization. Moreover, it is posited that when the data and/or the model may only exhibit $\\textit{approximate}$ or $\\textit{partial}$ symmetry, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17592","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/2305.17592/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":"2305.17592","created_at":"2026-07-05T10:50:40.377380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17592v2","created_at":"2026-07-05T10:50:40.377380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17592","created_at":"2026-07-05T10:50:40.377380+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QVME5O2NKQI","created_at":"2026-07-05T10:50:40.377380+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QVME5O2NKQIIWF2","created_at":"2026-07-05T10:50:40.377380+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QVME5O2","created_at":"2026-07-05T10:50:40.377380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU","json":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU.json","graph_json":"https://pith.science/api/pith-number/5QVME5O2NKQIIWF2ZZQGG3AEEU/graph.json","events_json":"https://pith.science/api/pith-number/5QVME5O2NKQIIWF2ZZQGG3AEEU/events.json","paper":"https://pith.science/paper/5QVME5O2"},"agent_actions":{"view_html":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU","download_json":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU.json","view_paper":"https://pith.science/paper/5QVME5O2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17592&json=true","fetch_graph":"https://pith.science/api/pith-number/5QVME5O2NKQIIWF2ZZQGG3AEEU/graph.json","fetch_events":"https://pith.science/api/pith-number/5QVME5O2NKQIIWF2ZZQGG3AEEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU/action/storage_attestation","attest_author":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU/action/author_attestation","sign_citation":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU/action/citation_signature","submit_replication":"https://pith.science/pith/5QVME5O2NKQIIWF2ZZQGG3AEEU/action/replication_record"}},"created_at":"2026-07-05T10:50:40.377380+00:00","updated_at":"2026-07-05T10:50:40.377380+00:00"}