{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NRGAK234FDS7YJFZ3J5S64E37V","short_pith_number":"pith:NRGAK234","schema_version":"1.0","canonical_sha256":"6c4c056b7c28e5fc24b9da7b2f709bfd565b16e5252001eff929617b2a9b4445","source":{"kind":"arxiv","id":"2410.09841","version":1},"attestation_state":"computed","paper":{"title":"Symmetry Discovery for Different Data Types","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lexiang Hu, Yikang Li, Zhouchen Lin","submitted_at":"2024-10-13T13:39:39Z","abstract_excerpt":"Equivariant neural networks incorporate symmetries into their architecture, achieving higher generalization performance. However, constructing equivariant neural networks typically requires prior knowledge of data types and symmetries, which is difficult to achieve in most tasks. In this paper, we propose LieSD, a method for discovering symmetries via trained neural networks which approximate the input-output mappings of the tasks. It characterizes equivariance and invariance (a special case of equivariance) of continuous groups using Lie algebra and directly solves the Lie algebra space throu"},"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":"2410.09841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T13:39:39Z","cross_cats_sorted":[],"title_canon_sha256":"2c6bd51ea6fe7bcaba73e422d35fc0922571c0234e762a2ab542304cf2d693ec","abstract_canon_sha256":"c7a051bb3c1ecfaf942337f364933c81fdd6b37bed048e89c3743c44ec7263af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:06.933660Z","signature_b64":"KnMDc7aSlHFkpg9xJSTdVYuNcJ1ZXw1UEsxefMPpJqGQ4KjeYm2hlLtNt3z7KHoOLGcKMpe9layMfkO43ZO4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c4c056b7c28e5fc24b9da7b2f709bfd565b16e5252001eff929617b2a9b4445","last_reissued_at":"2026-07-05T09:20:06.933200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:06.933200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetry Discovery for Different Data Types","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lexiang Hu, Yikang Li, Zhouchen Lin","submitted_at":"2024-10-13T13:39:39Z","abstract_excerpt":"Equivariant neural networks incorporate symmetries into their architecture, achieving higher generalization performance. However, constructing equivariant neural networks typically requires prior knowledge of data types and symmetries, which is difficult to achieve in most tasks. In this paper, we propose LieSD, a method for discovering symmetries via trained neural networks which approximate the input-output mappings of the tasks. It characterizes equivariance and invariance (a special case of equivariance) of continuous groups using Lie algebra and directly solves the Lie algebra space throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09841","kind":"arxiv","version":1},"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/2410.09841/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":"2410.09841","created_at":"2026-07-05T09:20:06.933256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09841v1","created_at":"2026-07-05T09:20:06.933256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09841","created_at":"2026-07-05T09:20:06.933256+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRGAK234FDS7","created_at":"2026-07-05T09:20:06.933256+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRGAK234FDS7YJFZ","created_at":"2026-07-05T09:20:06.933256+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRGAK234","created_at":"2026-07-05T09:20:06.933256+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/NRGAK234FDS7YJFZ3J5S64E37V","json":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V.json","graph_json":"https://pith.science/api/pith-number/NRGAK234FDS7YJFZ3J5S64E37V/graph.json","events_json":"https://pith.science/api/pith-number/NRGAK234FDS7YJFZ3J5S64E37V/events.json","paper":"https://pith.science/paper/NRGAK234"},"agent_actions":{"view_html":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V","download_json":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V.json","view_paper":"https://pith.science/paper/NRGAK234","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09841&json=true","fetch_graph":"https://pith.science/api/pith-number/NRGAK234FDS7YJFZ3J5S64E37V/graph.json","fetch_events":"https://pith.science/api/pith-number/NRGAK234FDS7YJFZ3J5S64E37V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V/action/storage_attestation","attest_author":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V/action/author_attestation","sign_citation":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V/action/citation_signature","submit_replication":"https://pith.science/pith/NRGAK234FDS7YJFZ3J5S64E37V/action/replication_record"}},"created_at":"2026-07-05T09:20:06.933256+00:00","updated_at":"2026-07-05T09:20:06.933256+00:00"}