{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AO56OL5RKSKU7GFD7GIT56ZMFQ","short_pith_number":"pith:AO56OL5R","schema_version":"1.0","canonical_sha256":"03bbe72fb154954f98a3f9913efb2c2c0b15202d47ab9364a4cec47ea8f7e3c2","source":{"kind":"arxiv","id":"2305.13665","version":1},"attestation_state":"computed","paper":{"title":"Dual Focal Loss for Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Linwei Tao, Minjing Dong","submitted_at":"2023-05-23T04:19:16Z","abstract_excerpt":"The use of deep neural networks in real-world applications require well-calibrated networks with confidence scores that accurately reflect the actual probability. However, it has been found that these networks often provide over-confident predictions, which leads to poor calibration. Recent efforts have sought to address this issue by focal loss to reduce over-confidence, but this approach can also lead to under-confident predictions. While different variants of focal loss have been explored, it is difficult to find a balance between over-confidence and under-confidence. In our work, we propos"},"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":"2305.13665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T04:19:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cba20639183bdf343cac24eb76e2df5c02436079309350faad62914be3ab55fd","abstract_canon_sha256":"dbb0404878c6a4bf60bc15521db6d90ddd0685a745982ee2dfdc80edd3841ba6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:55.874624Z","signature_b64":"oi/VLvPF0/GMjJEl8a3jW4o1IviMDNJs6DXdC+zXtEZvPjuGXsTig7b87t//nP0MwONUa0CkACFwXOaNmCqCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03bbe72fb154954f98a3f9913efb2c2c0b15202d47ab9364a4cec47ea8f7e3c2","last_reissued_at":"2026-07-05T06:12:55.874210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:55.874210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Focal Loss for Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Linwei Tao, Minjing Dong","submitted_at":"2023-05-23T04:19:16Z","abstract_excerpt":"The use of deep neural networks in real-world applications require well-calibrated networks with confidence scores that accurately reflect the actual probability. However, it has been found that these networks often provide over-confident predictions, which leads to poor calibration. Recent efforts have sought to address this issue by focal loss to reduce over-confidence, but this approach can also lead to under-confident predictions. While different variants of focal loss have been explored, it is difficult to find a balance between over-confidence and under-confidence. In our work, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13665","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/2305.13665/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":"2305.13665","created_at":"2026-07-05T06:12:55.874275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13665v1","created_at":"2026-07-05T06:12:55.874275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13665","created_at":"2026-07-05T06:12:55.874275+00:00"},{"alias_kind":"pith_short_12","alias_value":"AO56OL5RKSKU","created_at":"2026-07-05T06:12:55.874275+00:00"},{"alias_kind":"pith_short_16","alias_value":"AO56OL5RKSKU7GFD","created_at":"2026-07-05T06:12:55.874275+00:00"},{"alias_kind":"pith_short_8","alias_value":"AO56OL5R","created_at":"2026-07-05T06:12:55.874275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07400","citing_title":"A smart fridge with AI-enabled food computing","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ","json":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ.json","graph_json":"https://pith.science/api/pith-number/AO56OL5RKSKU7GFD7GIT56ZMFQ/graph.json","events_json":"https://pith.science/api/pith-number/AO56OL5RKSKU7GFD7GIT56ZMFQ/events.json","paper":"https://pith.science/paper/AO56OL5R"},"agent_actions":{"view_html":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ","download_json":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ.json","view_paper":"https://pith.science/paper/AO56OL5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13665&json=true","fetch_graph":"https://pith.science/api/pith-number/AO56OL5RKSKU7GFD7GIT56ZMFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AO56OL5RKSKU7GFD7GIT56ZMFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ/action/storage_attestation","attest_author":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ/action/author_attestation","sign_citation":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ/action/citation_signature","submit_replication":"https://pith.science/pith/AO56OL5RKSKU7GFD7GIT56ZMFQ/action/replication_record"}},"created_at":"2026-07-05T06:12:55.874275+00:00","updated_at":"2026-07-05T06:12:55.874275+00:00"}