{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RJ6JYTFYNCCKDTTMXZIL37FT6Q","short_pith_number":"pith:RJ6JYTFY","schema_version":"1.0","canonical_sha256":"8a7c9c4cb86884a1ce6cbe50bdfcb3f40555e7435771efa22160dcb0da82b79f","source":{"kind":"arxiv","id":"2210.04345","version":3},"attestation_state":"computed","paper":{"title":"LieGG: Studying Learned Lie Group Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Sepliarskaia, Arnold Smeulders, Artem Moskalev, Ivan Sosnovik","submitted_at":"2022-10-09T20:42:37Z","abstract_excerpt":"Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symmetries are not built into a model a priori, it is advantageous for robust networks to learn symmetries directly from the data to fit a task function. In this paper, we present a method to extract symmetries learned by a neural network and to evaluate the degree to which a network is invariant to them. With our method, we are able to explicitly retrieve learned invariances in a form of the generators of corresponding L"},"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":"2210.04345","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-09T20:42:37Z","cross_cats_sorted":[],"title_canon_sha256":"93c718dd872d727414e62f54c3bb3faaa4e9dc8ebc20e31a3e7dbe7057302bb7","abstract_canon_sha256":"cdd6eabe62ba1f7cec42d465439c3a24052866f22999e5a6d6a9773623d6bb22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:09.215370Z","signature_b64":"fH6zjig25r5tzfIcXaX6JOU4xOIk3vTb0O2n4HVASKeEE0fFiX9E+zEYPwPHmskptYE2aMj5lCZDDNB4KDz0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7c9c4cb86884a1ce6cbe50bdfcb3f40555e7435771efa22160dcb0da82b79f","last_reissued_at":"2026-07-05T05:37:09.214825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:09.214825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LieGG: Studying Learned Lie Group Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Sepliarskaia, Arnold Smeulders, Artem Moskalev, Ivan Sosnovik","submitted_at":"2022-10-09T20:42:37Z","abstract_excerpt":"Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symmetries are not built into a model a priori, it is advantageous for robust networks to learn symmetries directly from the data to fit a task function. In this paper, we present a method to extract symmetries learned by a neural network and to evaluate the degree to which a network is invariant to them. With our method, we are able to explicitly retrieve learned invariances in a form of the generators of corresponding L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04345","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/2210.04345/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":"2210.04345","created_at":"2026-07-05T05:37:09.214883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04345v3","created_at":"2026-07-05T05:37:09.214883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04345","created_at":"2026-07-05T05:37:09.214883+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ6JYTFYNCCK","created_at":"2026-07-05T05:37:09.214883+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ6JYTFYNCCKDTTM","created_at":"2026-07-05T05:37:09.214883+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ6JYTFY","created_at":"2026-07-05T05:37:09.214883+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/RJ6JYTFYNCCKDTTMXZIL37FT6Q","json":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q.json","graph_json":"https://pith.science/api/pith-number/RJ6JYTFYNCCKDTTMXZIL37FT6Q/graph.json","events_json":"https://pith.science/api/pith-number/RJ6JYTFYNCCKDTTMXZIL37FT6Q/events.json","paper":"https://pith.science/paper/RJ6JYTFY"},"agent_actions":{"view_html":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q","download_json":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q.json","view_paper":"https://pith.science/paper/RJ6JYTFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04345&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ6JYTFYNCCKDTTMXZIL37FT6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ6JYTFYNCCKDTTMXZIL37FT6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q/action/storage_attestation","attest_author":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q/action/author_attestation","sign_citation":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q/action/citation_signature","submit_replication":"https://pith.science/pith/RJ6JYTFYNCCKDTTMXZIL37FT6Q/action/replication_record"}},"created_at":"2026-07-05T05:37:09.214883+00:00","updated_at":"2026-07-05T05:37:09.214883+00:00"}