{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G6N4WB5MBPWLASGCVODWBRCXLV","short_pith_number":"pith:G6N4WB5M","schema_version":"1.0","canonical_sha256":"379bcb07ac0becb048c2ab8760c4575d51b8248c3164a7d0973d523f6924262e","source":{"kind":"arxiv","id":"2302.06245","version":2},"attestation_state":"computed","paper":{"title":"Calibrating a Deep Neural Network with Its Predecessors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changming Sun, Chang Xu, Daochang Liu, Linwei Tao, Minjing Dong","submitted_at":"2023-02-13T10:33:55Z","abstract_excerpt":"Confidence calibration - the process to calibrate the output probability distribution of neural networks - is essential for safety-critical applications of such networks. Recent works verify the link between mis-calibration and overfitting. However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks. In this work, we study the limitions of early stopping and comprehensively analyze the overfitting problem of a network considering each individual block. We then propose a novel regularization method, predecessor combination search (PCS), to improve cal"},"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":"2302.06245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T10:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"0d9403285da6fa9e3128d855ded3a35d0feb0f623df99e41f7c50948255f1d76","abstract_canon_sha256":"a76769e50741a2c2b8251c2f7002bb0032c62c2e92a38d997b06afd5f776b955"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:44.544217Z","signature_b64":"OKfHXTaTXT2pZOHlM8X5rvhjFfpn0IQgwamaIBPrL+o8laLezs38KAqAhqGqsfQSPP3M7slvE/p+Os6HF+uRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"379bcb07ac0becb048c2ab8760c4575d51b8248c3164a7d0973d523f6924262e","last_reissued_at":"2026-07-05T06:12:44.543812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:44.543812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrating a Deep Neural Network with Its Predecessors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changming Sun, Chang Xu, Daochang Liu, Linwei Tao, Minjing Dong","submitted_at":"2023-02-13T10:33:55Z","abstract_excerpt":"Confidence calibration - the process to calibrate the output probability distribution of neural networks - is essential for safety-critical applications of such networks. Recent works verify the link between mis-calibration and overfitting. However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks. In this work, we study the limitions of early stopping and comprehensively analyze the overfitting problem of a network considering each individual block. We then propose a novel regularization method, predecessor combination search (PCS), to improve cal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06245","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/2302.06245/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":"2302.06245","created_at":"2026-07-05T06:12:44.543876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06245v2","created_at":"2026-07-05T06:12:44.543876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06245","created_at":"2026-07-05T06:12:44.543876+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6N4WB5MBPWL","created_at":"2026-07-05T06:12:44.543876+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6N4WB5MBPWLASGC","created_at":"2026-07-05T06:12:44.543876+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6N4WB5M","created_at":"2026-07-05T06:12:44.543876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15301","citing_title":"Parametric $\\rho$-Norm Scaling Calibration","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV","json":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV.json","graph_json":"https://pith.science/api/pith-number/G6N4WB5MBPWLASGCVODWBRCXLV/graph.json","events_json":"https://pith.science/api/pith-number/G6N4WB5MBPWLASGCVODWBRCXLV/events.json","paper":"https://pith.science/paper/G6N4WB5M"},"agent_actions":{"view_html":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV","download_json":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV.json","view_paper":"https://pith.science/paper/G6N4WB5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06245&json=true","fetch_graph":"https://pith.science/api/pith-number/G6N4WB5MBPWLASGCVODWBRCXLV/graph.json","fetch_events":"https://pith.science/api/pith-number/G6N4WB5MBPWLASGCVODWBRCXLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV/action/storage_attestation","attest_author":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV/action/author_attestation","sign_citation":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV/action/citation_signature","submit_replication":"https://pith.science/pith/G6N4WB5MBPWLASGCVODWBRCXLV/action/replication_record"}},"created_at":"2026-07-05T06:12:44.543876+00:00","updated_at":"2026-07-05T06:12:44.543876+00:00"}