{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DYKFZ5EJRPNW26YZZA3UPCS3HG","short_pith_number":"pith:DYKFZ5EJ","schema_version":"1.0","canonical_sha256":"1e145cf4898bdb6d7b19c837478a5b39874b67bfc4a1b592ce570acd276d17d6","source":{"kind":"arxiv","id":"2501.07930","version":3},"attestation_state":"computed","paper":{"title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Agustin Martin Picard, Franck Mamalet, Mathieu Serrurier (IRIT), Thibaut Boissin (IRIT), Thomas Fel, Thomas Massena (IRIT)","submitted_at":"2025-01-14T08:32:12Z","abstract_excerpt":"Orthogonal convolutional layers are valuable components in multiple areas of machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitz-constrained models. Their ability to preserve norms and ensure stable gradient propagation makes them valuable for a large range of problems. Despite their promise, the deployment of orthogonal convolution in large-scale applications is a significant challenge due to computational overhead and limited support for modern features like strides, dilations, group convolutions, and transposed convolutions. In this paper, we introduce A"},"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":"2501.07930","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-14T08:32:12Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"33ec8382eed5c6b0ddfb7cf9573d6521d2cce012427eda1362c1ca80b60c5608","abstract_canon_sha256":"b58e6e715f01fa07cd1d55ccb74edf8bbfb3dd321f126e26cb66a7a375145dfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:41.723963Z","signature_b64":"w7He3iWcAnjfQe8bmMhS6Cs+No+7jR0gxNaLBpLjPbtlnJAQac8y9vmQbb1JlJa8N62W30rQKAGlcsQjkv46CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e145cf4898bdb6d7b19c837478a5b39874b67bfc4a1b592ce570acd276d17d6","last_reissued_at":"2026-07-05T11:15:41.723450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:41.723450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Agustin Martin Picard, Franck Mamalet, Mathieu Serrurier (IRIT), Thibaut Boissin (IRIT), Thomas Fel, Thomas Massena (IRIT)","submitted_at":"2025-01-14T08:32:12Z","abstract_excerpt":"Orthogonal convolutional layers are valuable components in multiple areas of machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitz-constrained models. Their ability to preserve norms and ensure stable gradient propagation makes them valuable for a large range of problems. Despite their promise, the deployment of orthogonal convolution in large-scale applications is a significant challenge due to computational overhead and limited support for modern features like strides, dilations, group convolutions, and transposed convolutions. In this paper, we introduce A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07930","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/2501.07930/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":"2501.07930","created_at":"2026-07-05T11:15:41.723507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07930v3","created_at":"2026-07-05T11:15:41.723507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07930","created_at":"2026-07-05T11:15:41.723507+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYKFZ5EJRPNW","created_at":"2026-07-05T11:15:41.723507+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYKFZ5EJRPNW26YZ","created_at":"2026-07-05T11:15:41.723507+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYKFZ5EJ","created_at":"2026-07-05T11:15:41.723507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02879","citing_title":"Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG","json":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG.json","graph_json":"https://pith.science/api/pith-number/DYKFZ5EJRPNW26YZZA3UPCS3HG/graph.json","events_json":"https://pith.science/api/pith-number/DYKFZ5EJRPNW26YZZA3UPCS3HG/events.json","paper":"https://pith.science/paper/DYKFZ5EJ"},"agent_actions":{"view_html":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG","download_json":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG.json","view_paper":"https://pith.science/paper/DYKFZ5EJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07930&json=true","fetch_graph":"https://pith.science/api/pith-number/DYKFZ5EJRPNW26YZZA3UPCS3HG/graph.json","fetch_events":"https://pith.science/api/pith-number/DYKFZ5EJRPNW26YZZA3UPCS3HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG/action/storage_attestation","attest_author":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG/action/author_attestation","sign_citation":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG/action/citation_signature","submit_replication":"https://pith.science/pith/DYKFZ5EJRPNW26YZZA3UPCS3HG/action/replication_record"}},"created_at":"2026-07-05T11:15:41.723507+00:00","updated_at":"2026-07-05T11:15:41.723507+00:00"}