{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FYHZTUXQ45OAHOVYLRJAP7M3OX","short_pith_number":"pith:FYHZTUXQ","schema_version":"1.0","canonical_sha256":"2e0f99d2f0e75c03bab85c5207fd9b75f5bb4fc09fb3befce9b1c5976b431bdd","source":{"kind":"arxiv","id":"2308.08366","version":1},"attestation_state":"computed","paper":{"title":"Dual-Branch Temperature Scaling Calibration for Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jialin Guo, Yang Ji, Zhenyu Wu, Zhiqiang Zhan","submitted_at":"2023-08-16T13:40:58Z","abstract_excerpt":"The calibration for deep neural networks is currently receiving widespread attention and research. Miscalibration usually leads to overconfidence of the model. While, under the condition of long-tailed distribution of data, the problem of miscalibration is more prominent due to the different confidence levels of samples in minority and majority categories, and it will result in more serious overconfidence. To address this problem, some current research have designed diverse temperature coefficients for different categories based on temperature scaling (TS) method. However, in the case of rare "},"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":"2308.08366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-16T13:40:58Z","cross_cats_sorted":[],"title_canon_sha256":"bf165335cd8a83daef65339c2e02d33539e84f96296a2865db9d85231ae69363","abstract_canon_sha256":"f24b03f4874b5a74adbcd9ad86e53773c57601ea7d58ff1c6141c699c720fcae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:58.419984Z","signature_b64":"yjhP2tLXUXSQDH3uUXT8nzrlRzsvNQbPx8Oo6gH2uYnEwcof3P7hByrLdMq2vEtkUuUxYWcmvnm0RPBvtWEbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e0f99d2f0e75c03bab85c5207fd9b75f5bb4fc09fb3befce9b1c5976b431bdd","last_reissued_at":"2026-07-05T06:41:58.419500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:58.419500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Branch Temperature Scaling Calibration for Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jialin Guo, Yang Ji, Zhenyu Wu, Zhiqiang Zhan","submitted_at":"2023-08-16T13:40:58Z","abstract_excerpt":"The calibration for deep neural networks is currently receiving widespread attention and research. Miscalibration usually leads to overconfidence of the model. While, under the condition of long-tailed distribution of data, the problem of miscalibration is more prominent due to the different confidence levels of samples in minority and majority categories, and it will result in more serious overconfidence. To address this problem, some current research have designed diverse temperature coefficients for different categories based on temperature scaling (TS) method. However, in the case of rare "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08366","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/2308.08366/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":"2308.08366","created_at":"2026-07-05T06:41:58.419559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08366v1","created_at":"2026-07-05T06:41:58.419559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08366","created_at":"2026-07-05T06:41:58.419559+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYHZTUXQ45OA","created_at":"2026-07-05T06:41:58.419559+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYHZTUXQ45OAHOVY","created_at":"2026-07-05T06:41:58.419559+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYHZTUXQ","created_at":"2026-07-05T06:41:58.419559+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/FYHZTUXQ45OAHOVYLRJAP7M3OX","json":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX.json","graph_json":"https://pith.science/api/pith-number/FYHZTUXQ45OAHOVYLRJAP7M3OX/graph.json","events_json":"https://pith.science/api/pith-number/FYHZTUXQ45OAHOVYLRJAP7M3OX/events.json","paper":"https://pith.science/paper/FYHZTUXQ"},"agent_actions":{"view_html":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX","download_json":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX.json","view_paper":"https://pith.science/paper/FYHZTUXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08366&json=true","fetch_graph":"https://pith.science/api/pith-number/FYHZTUXQ45OAHOVYLRJAP7M3OX/graph.json","fetch_events":"https://pith.science/api/pith-number/FYHZTUXQ45OAHOVYLRJAP7M3OX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX/action/storage_attestation","attest_author":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX/action/author_attestation","sign_citation":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX/action/citation_signature","submit_replication":"https://pith.science/pith/FYHZTUXQ45OAHOVYLRJAP7M3OX/action/replication_record"}},"created_at":"2026-07-05T06:41:58.419559+00:00","updated_at":"2026-07-05T06:41:58.419559+00:00"}