{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DZMTYVHNWLTJKHBIXVFLQLJ7CO","short_pith_number":"pith:DZMTYVHN","schema_version":"1.0","canonical_sha256":"1e593c54edb2e6951c28bd4ab82d3f138cff5dd16d35e866144023f3004646e4","source":{"kind":"arxiv","id":"2009.10762","version":1},"attestation_state":"computed","paper":{"title":"Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirudh Som, Hongjun Choi, Pavan Turaga","submitted_at":"2020-09-22T18:46:05Z","abstract_excerpt":"Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained often exhibit issues like feature redundancy, low interpretability, and poor calibration. A body of recent work has emerged that has tried addressing some of these challenges by proposing the use of new regularization functions in addition to the cross-entropy loss. In this paper, we present some surprising findings that emerge from exploring the role of simple orthogonality constraints as a means of imposing physics-m"},"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":"2009.10762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-22T18:46:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7dd59c48c8b1ef529416e2a8ed12f50e6a925032b8b9e2d8346eee49aa659216","abstract_canon_sha256":"d882f2965879714a167e010464e0582448b142245493e10ddc8416964936a7b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:25.649760Z","signature_b64":"6LAFQGYPOQLf8ioaGhE7nwWoV4bsk6DXNeAG254U0nQyKASyMfc5tJPOYYPUSVI0qxa71gwNhkj9hnpw3r0NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e593c54edb2e6951c28bd4ab82d3f138cff5dd16d35e866144023f3004646e4","last_reissued_at":"2026-07-05T01:37:25.649304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:25.649304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirudh Som, Hongjun Choi, Pavan Turaga","submitted_at":"2020-09-22T18:46:05Z","abstract_excerpt":"Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained often exhibit issues like feature redundancy, low interpretability, and poor calibration. A body of recent work has emerged that has tried addressing some of these challenges by proposing the use of new regularization functions in addition to the cross-entropy loss. In this paper, we present some surprising findings that emerge from exploring the role of simple orthogonality constraints as a means of imposing physics-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10762","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/2009.10762/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":"2009.10762","created_at":"2026-07-05T01:37:25.649368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.10762v1","created_at":"2026-07-05T01:37:25.649368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10762","created_at":"2026-07-05T01:37:25.649368+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZMTYVHNWLTJ","created_at":"2026-07-05T01:37:25.649368+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZMTYVHNWLTJKHBI","created_at":"2026-07-05T01:37:25.649368+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZMTYVHN","created_at":"2026-07-05T01:37:25.649368+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/DZMTYVHNWLTJKHBIXVFLQLJ7CO","json":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO.json","graph_json":"https://pith.science/api/pith-number/DZMTYVHNWLTJKHBIXVFLQLJ7CO/graph.json","events_json":"https://pith.science/api/pith-number/DZMTYVHNWLTJKHBIXVFLQLJ7CO/events.json","paper":"https://pith.science/paper/DZMTYVHN"},"agent_actions":{"view_html":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO","download_json":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO.json","view_paper":"https://pith.science/paper/DZMTYVHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.10762&json=true","fetch_graph":"https://pith.science/api/pith-number/DZMTYVHNWLTJKHBIXVFLQLJ7CO/graph.json","fetch_events":"https://pith.science/api/pith-number/DZMTYVHNWLTJKHBIXVFLQLJ7CO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO/action/storage_attestation","attest_author":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO/action/author_attestation","sign_citation":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO/action/citation_signature","submit_replication":"https://pith.science/pith/DZMTYVHNWLTJKHBIXVFLQLJ7CO/action/replication_record"}},"created_at":"2026-07-05T01:37:25.649368+00:00","updated_at":"2026-07-05T01:37:25.649368+00:00"}