{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TXND7PUK6HCEBKOPRTTDMTASY3","short_pith_number":"pith:TXND7PUK","schema_version":"1.0","canonical_sha256":"9dda3fbe8af1c440a9cf8ce6364c12c6c5f880b92015bf0ec31ad619b7b08aaf","source":{"kind":"arxiv","id":"2104.05508","version":1},"attestation_state":"computed","paper":{"title":"Noether: The More Things Change, the More Stay the Same","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Grzegorz G{\\l}uch, R\\\"udiger Urbanke","submitted_at":"2021-04-12T14:41:05Z","abstract_excerpt":"Symmetries have proven to be important ingredients in the analysis of neural networks. So far their use has mostly been implicit or seemingly coincidental.\n  We undertake a systematic study of the role that symmetry plays. In particular, we clarify how symmetry interacts with the learning algorithm. The key ingredient in our study is played by Noether's celebrated theorem which, informally speaking, states that symmetry leads to conserved quantities (e.g., conservation of energy or conservation of momentum). In the realm of neural networks under gradient descent, model symmetries imply restric"},"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":"2104.05508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T14:41:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"690f6b471f50e4b06605d6e950b474f6f88aaeee62af46cae40bb27e3391d984","abstract_canon_sha256":"55ed4b4926b12c9c9b453fdabb812db9313fcb7c0800c1a52c72735ab2c614b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:13.431215Z","signature_b64":"Iotatm1GbBA4+oSPz7UXihUViTL5r41QUZN94t+BuS5u9qcdzMzkFAykU+/0le9GXagrEWbf9mjxOUd7lpl/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dda3fbe8af1c440a9cf8ce6364c12c6c5f880b92015bf0ec31ad619b7b08aaf","last_reissued_at":"2026-07-05T02:31:13.430705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:13.430705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noether: The More Things Change, the More Stay the Same","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Grzegorz G{\\l}uch, R\\\"udiger Urbanke","submitted_at":"2021-04-12T14:41:05Z","abstract_excerpt":"Symmetries have proven to be important ingredients in the analysis of neural networks. So far their use has mostly been implicit or seemingly coincidental.\n  We undertake a systematic study of the role that symmetry plays. In particular, we clarify how symmetry interacts with the learning algorithm. The key ingredient in our study is played by Noether's celebrated theorem which, informally speaking, states that symmetry leads to conserved quantities (e.g., conservation of energy or conservation of momentum). In the realm of neural networks under gradient descent, model symmetries imply restric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05508","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/2104.05508/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":"2104.05508","created_at":"2026-07-05T02:31:13.430769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05508v1","created_at":"2026-07-05T02:31:13.430769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05508","created_at":"2026-07-05T02:31:13.430769+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXND7PUK6HCE","created_at":"2026-07-05T02:31:13.430769+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXND7PUK6HCEBKOP","created_at":"2026-07-05T02:31:13.430769+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXND7PUK","created_at":"2026-07-05T02:31:13.430769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10913","citing_title":"Conservation Laws from Data Symmetry in Neural Networks","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3","json":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3.json","graph_json":"https://pith.science/api/pith-number/TXND7PUK6HCEBKOPRTTDMTASY3/graph.json","events_json":"https://pith.science/api/pith-number/TXND7PUK6HCEBKOPRTTDMTASY3/events.json","paper":"https://pith.science/paper/TXND7PUK"},"agent_actions":{"view_html":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3","download_json":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3.json","view_paper":"https://pith.science/paper/TXND7PUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05508&json=true","fetch_graph":"https://pith.science/api/pith-number/TXND7PUK6HCEBKOPRTTDMTASY3/graph.json","fetch_events":"https://pith.science/api/pith-number/TXND7PUK6HCEBKOPRTTDMTASY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3/action/storage_attestation","attest_author":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3/action/author_attestation","sign_citation":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3/action/citation_signature","submit_replication":"https://pith.science/pith/TXND7PUK6HCEBKOPRTTDMTASY3/action/replication_record"}},"created_at":"2026-07-05T02:31:13.430769+00:00","updated_at":"2026-07-05T02:31:13.430769+00:00"}