{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WLOPBSHVGLJU7GO22OPP4RKP7D","short_pith_number":"pith:WLOPBSHV","schema_version":"1.0","canonical_sha256":"b2dcf0c8f532d34f99dad39efe454ff8d3157238c47fa081db82b667fafc0b87","source":{"kind":"arxiv","id":"2308.11911","version":2},"attestation_state":"computed","paper":{"title":"ACLS: Adaptive and Conditional Label Smoothing for Network Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, DongHyeon Baek, Hyekang Park, Jongyoun Noh, Youngmin Oh","submitted_at":"2023-08-23T04:52:48Z","abstract_excerpt":"We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based method that exploits a regularization term to smooth the miscalibrated confidences. Although these approaches have shown the effectiveness on calibrating the networks, there is still a lack of understanding on the underlying principles of regularization in terms of network calibration. We present in this paper an in-depth analysis of existing regularization-based methods, providing a better understanding on how they affec"},"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":"2308.11911","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T04:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"f4c96baa839f3a84324bf5728305f14bb32d75149f5e463a4c5f87d03425cc57","abstract_canon_sha256":"7271706bde9bd8fc19649f36b1bfcdd6ed85d84e42cee6861766b81ef51b86d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:09.368144Z","signature_b64":"KBg9IX76xeZ9d+wet/qqK/1mPmB2LapicvHeY0WDGCeTfAwCF6ZEu+QpucWUU7vinyyzvdkEsdQjiqVmJzA6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2dcf0c8f532d34f99dad39efe454ff8d3157238c47fa081db82b667fafc0b87","last_reissued_at":"2026-07-05T06:44:09.367680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:09.367680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACLS: Adaptive and Conditional Label Smoothing for Network Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, DongHyeon Baek, Hyekang Park, Jongyoun Noh, Youngmin Oh","submitted_at":"2023-08-23T04:52:48Z","abstract_excerpt":"We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based method that exploits a regularization term to smooth the miscalibrated confidences. Although these approaches have shown the effectiveness on calibrating the networks, there is still a lack of understanding on the underlying principles of regularization in terms of network calibration. We present in this paper an in-depth analysis of existing regularization-based methods, providing a better understanding on how they affec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11911","kind":"arxiv","version":2},"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/2308.11911/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":"2308.11911","created_at":"2026-07-05T06:44:09.367745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11911v2","created_at":"2026-07-05T06:44:09.367745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11911","created_at":"2026-07-05T06:44:09.367745+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLOPBSHVGLJU","created_at":"2026-07-05T06:44:09.367745+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLOPBSHVGLJU7GO2","created_at":"2026-07-05T06:44:09.367745+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLOPBSHV","created_at":"2026-07-05T06:44:09.367745+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/WLOPBSHVGLJU7GO22OPP4RKP7D","json":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D.json","graph_json":"https://pith.science/api/pith-number/WLOPBSHVGLJU7GO22OPP4RKP7D/graph.json","events_json":"https://pith.science/api/pith-number/WLOPBSHVGLJU7GO22OPP4RKP7D/events.json","paper":"https://pith.science/paper/WLOPBSHV"},"agent_actions":{"view_html":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D","download_json":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D.json","view_paper":"https://pith.science/paper/WLOPBSHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11911&json=true","fetch_graph":"https://pith.science/api/pith-number/WLOPBSHVGLJU7GO22OPP4RKP7D/graph.json","fetch_events":"https://pith.science/api/pith-number/WLOPBSHVGLJU7GO22OPP4RKP7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D/action/storage_attestation","attest_author":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D/action/author_attestation","sign_citation":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D/action/citation_signature","submit_replication":"https://pith.science/pith/WLOPBSHVGLJU7GO22OPP4RKP7D/action/replication_record"}},"created_at":"2026-07-05T06:44:09.367745+00:00","updated_at":"2026-07-05T06:44:09.367745+00:00"}