{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VUIFTP26BK5SD3AMXUKZTK44GQ","short_pith_number":"pith:VUIFTP26","schema_version":"1.0","canonical_sha256":"ad1059bf5e0abb21ec0cbd1599ab9c34023b0806bf3c77728744b658a856b9b2","source":{"kind":"arxiv","id":"2408.13242","version":2},"attestation_state":"computed","paper":{"title":"Improving Equivariant Model Training via Constraint Relaxation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Evangelos Chatzipantazis, Kostas Daniilidis, Shubhendu Trivedi, Stefanos Pertigkiozoglou","submitted_at":"2024-08-23T17:35:08Z","abstract_excerpt":"Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Despite their successes, such networks can be difficult to optimize and require careful hyperparameter tuning to train successfully. In this work, we propose a novel framework for improving the optimization of such models by relaxing the hard equivariance constraint during training: We relax the equivariance constraint of the network's intermediate layers by introducing an additional non-equivariant term that we progress"},"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":"2408.13242","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T17:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"70b3c64499b4c959af5ad2cdacc778ad2b61fbf8f36e46790b7e52059a3cd965","abstract_canon_sha256":"147a3018f648719651fc44886666e8b412d18a5625117ee162d2246f227800a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:21.856075Z","signature_b64":"1TsdqvJ8Yzw43zBV6wCL2WMqTQmUCxC2Bn5wh9Pgc6pNthvtJLTGSZ9KnF5yn1AYSlaav34QBWE/lqs9u0CBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad1059bf5e0abb21ec0cbd1599ab9c34023b0806bf3c77728744b658a856b9b2","last_reissued_at":"2026-07-05T09:56:21.855617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:21.855617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Equivariant Model Training via Constraint Relaxation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Evangelos Chatzipantazis, Kostas Daniilidis, Shubhendu Trivedi, Stefanos Pertigkiozoglou","submitted_at":"2024-08-23T17:35:08Z","abstract_excerpt":"Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Despite their successes, such networks can be difficult to optimize and require careful hyperparameter tuning to train successfully. In this work, we propose a novel framework for improving the optimization of such models by relaxing the hard equivariance constraint during training: We relax the equivariance constraint of the network's intermediate layers by introducing an additional non-equivariant term that we progress"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13242","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/2408.13242/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":"2408.13242","created_at":"2026-07-05T09:56:21.855675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13242v2","created_at":"2026-07-05T09:56:21.855675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13242","created_at":"2026-07-05T09:56:21.855675+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUIFTP26BK5S","created_at":"2026-07-05T09:56:21.855675+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUIFTP26BK5SD3AM","created_at":"2026-07-05T09:56:21.855675+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUIFTP26","created_at":"2026-07-05T09:56:21.855675+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/VUIFTP26BK5SD3AMXUKZTK44GQ","json":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ.json","graph_json":"https://pith.science/api/pith-number/VUIFTP26BK5SD3AMXUKZTK44GQ/graph.json","events_json":"https://pith.science/api/pith-number/VUIFTP26BK5SD3AMXUKZTK44GQ/events.json","paper":"https://pith.science/paper/VUIFTP26"},"agent_actions":{"view_html":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ","download_json":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ.json","view_paper":"https://pith.science/paper/VUIFTP26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13242&json=true","fetch_graph":"https://pith.science/api/pith-number/VUIFTP26BK5SD3AMXUKZTK44GQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VUIFTP26BK5SD3AMXUKZTK44GQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ/action/storage_attestation","attest_author":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ/action/author_attestation","sign_citation":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ/action/citation_signature","submit_replication":"https://pith.science/pith/VUIFTP26BK5SD3AMXUKZTK44GQ/action/replication_record"}},"created_at":"2026-07-05T09:56:21.855675+00:00","updated_at":"2026-07-05T09:56:21.855675+00:00"}