{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W2NHZ5IRI4EYZXQQDPTZCR2G55","short_pith_number":"pith:W2NHZ5IR","schema_version":"1.0","canonical_sha256":"b69a7cf51147098cde101be7914746ef4f0708a7f02b189913e6372c110ba891","source":{"kind":"arxiv","id":"2403.07289","version":1},"attestation_state":"computed","paper":{"title":"Rediscovering BCE Loss for Uniform Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancan Zhou, Jinming Duan, Linlin Shen, Qiufu Li, Xi Jia","submitted_at":"2024-03-12T03:44:40Z","abstract_excerpt":"This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model's performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classific"},"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":"2403.07289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T03:44:40Z","cross_cats_sorted":[],"title_canon_sha256":"85dc4180eddf0a33d726f1a5a2011b33f5017f912320ca638148a2d586994f41","abstract_canon_sha256":"6a67ed08f6b03d5ff829214e3f0bbf435223e7b42cdfa2cddee649fb61acc581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:01.731001Z","signature_b64":"1ptRZ/mBT2maYVz186H1UcAMWwgH8QtXrpUTzUcfNLnXtZR5Db8/kWyn3U1y5LDkCgmbpIuf7f+tLBJVkmx/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b69a7cf51147098cde101be7914746ef4f0708a7f02b189913e6372c110ba891","last_reissued_at":"2026-07-05T07:55:01.730505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:01.730505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rediscovering BCE Loss for Uniform Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancan Zhou, Jinming Duan, Linlin Shen, Qiufu Li, Xi Jia","submitted_at":"2024-03-12T03:44:40Z","abstract_excerpt":"This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model's performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07289","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/2403.07289/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":"2403.07289","created_at":"2026-07-05T07:55:01.730564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07289v1","created_at":"2026-07-05T07:55:01.730564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07289","created_at":"2026-07-05T07:55:01.730564+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2NHZ5IRI4EY","created_at":"2026-07-05T07:55:01.730564+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2NHZ5IRI4EYZXQQ","created_at":"2026-07-05T07:55:01.730564+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2NHZ5IR","created_at":"2026-07-05T07:55:01.730564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14926","citing_title":"SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55","json":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55.json","graph_json":"https://pith.science/api/pith-number/W2NHZ5IRI4EYZXQQDPTZCR2G55/graph.json","events_json":"https://pith.science/api/pith-number/W2NHZ5IRI4EYZXQQDPTZCR2G55/events.json","paper":"https://pith.science/paper/W2NHZ5IR"},"agent_actions":{"view_html":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55","download_json":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55.json","view_paper":"https://pith.science/paper/W2NHZ5IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07289&json=true","fetch_graph":"https://pith.science/api/pith-number/W2NHZ5IRI4EYZXQQDPTZCR2G55/graph.json","fetch_events":"https://pith.science/api/pith-number/W2NHZ5IRI4EYZXQQDPTZCR2G55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55/action/storage_attestation","attest_author":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55/action/author_attestation","sign_citation":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55/action/citation_signature","submit_replication":"https://pith.science/pith/W2NHZ5IRI4EYZXQQDPTZCR2G55/action/replication_record"}},"created_at":"2026-07-05T07:55:01.730564+00:00","updated_at":"2026-07-05T07:55:01.730564+00:00"}