{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5WZVOADHSQ6CTRL5TJQGOPHVPR","short_pith_number":"pith:5WZVOADH","schema_version":"1.0","canonical_sha256":"edb3570067943c29c57d9a60673cf57c532e5a87d355e35dccb08b7b85eca1b1","source":{"kind":"arxiv","id":"2306.00356","version":1},"attestation_state":"computed","paper":{"title":"Regularizing Towards Soft Equivariance Under Mixed Symmetries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongseok Yang, Hyungi Lee, Hyunsu Kim, Juho Lee","submitted_at":"2023-06-01T05:33:41Z","abstract_excerpt":"Datasets often have their intrinsic symmetries, and particular deep-learning models called equivariant or invariant models have been developed to exploit these symmetries. However, if some or all of these symmetries are only approximate, which frequently happens in practice, these models may be suboptimal due to the architectural restrictions imposed on them. We tackle this issue of approximate symmetries in a setup where symmetries are mixed, i.e., they are symmetries of not single but multiple different types and the degree of approximation varies across these types. Instead of proposing a n"},"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":"2306.00356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T05:33:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6ce905a8cf0c270c94ea7ec71b62f9876c3cd7ed4167a7fcd7df4e5d18bf4b20","abstract_canon_sha256":"94e7c3c9b96c2ecbd7c4e0f8c7b534b37a5f8f8a88085cf73ff72049870dd70d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:25.353498Z","signature_b64":"cnW6ujYdmnF16Z0ELmp1NBACBjPE2j/XlnXXvWWJDhU8y4DWZc903qEolQMskBLK9lhXkrhX2MRceBaNlk17DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb3570067943c29c57d9a60673cf57c532e5a87d355e35dccb08b7b85eca1b1","last_reissued_at":"2026-07-05T06:16:25.353008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:25.353008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularizing Towards Soft Equivariance Under Mixed Symmetries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongseok Yang, Hyungi Lee, Hyunsu Kim, Juho Lee","submitted_at":"2023-06-01T05:33:41Z","abstract_excerpt":"Datasets often have their intrinsic symmetries, and particular deep-learning models called equivariant or invariant models have been developed to exploit these symmetries. However, if some or all of these symmetries are only approximate, which frequently happens in practice, these models may be suboptimal due to the architectural restrictions imposed on them. We tackle this issue of approximate symmetries in a setup where symmetries are mixed, i.e., they are symmetries of not single but multiple different types and the degree of approximation varies across these types. Instead of proposing a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00356","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/2306.00356/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":"2306.00356","created_at":"2026-07-05T06:16:25.353066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00356v1","created_at":"2026-07-05T06:16:25.353066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00356","created_at":"2026-07-05T06:16:25.353066+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WZVOADHSQ6C","created_at":"2026-07-05T06:16:25.353066+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WZVOADHSQ6CTRL5","created_at":"2026-07-05T06:16:25.353066+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WZVOADH","created_at":"2026-07-05T06:16:25.353066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR","json":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR.json","graph_json":"https://pith.science/api/pith-number/5WZVOADHSQ6CTRL5TJQGOPHVPR/graph.json","events_json":"https://pith.science/api/pith-number/5WZVOADHSQ6CTRL5TJQGOPHVPR/events.json","paper":"https://pith.science/paper/5WZVOADH"},"agent_actions":{"view_html":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR","download_json":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR.json","view_paper":"https://pith.science/paper/5WZVOADH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00356&json=true","fetch_graph":"https://pith.science/api/pith-number/5WZVOADHSQ6CTRL5TJQGOPHVPR/graph.json","fetch_events":"https://pith.science/api/pith-number/5WZVOADHSQ6CTRL5TJQGOPHVPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR/action/storage_attestation","attest_author":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR/action/author_attestation","sign_citation":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR/action/citation_signature","submit_replication":"https://pith.science/pith/5WZVOADHSQ6CTRL5TJQGOPHVPR/action/replication_record"}},"created_at":"2026-07-05T06:16:25.353066+00:00","updated_at":"2026-07-05T06:16:25.353066+00:00"}