{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IGZYJHKQ5UOBW6SHN3TFF3CS4A","short_pith_number":"pith:IGZYJHKQ","schema_version":"1.0","canonical_sha256":"41b3849d50ed1c1b7a476ee652ec52e003914fbe00d821440c1763434fd6b17f","source":{"kind":"arxiv","id":"2308.01222","version":4},"attestation_state":"computed","paper":{"title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng Wang","submitted_at":"2023-08-02T15:28:10Z","abstract_excerpt":"Calibrating deep neural models plays an important role in building reliable, robust AI systems in safety-critical applications. Recent work has shown that modern neural networks that possess high predictive capability are poorly calibrated and produce unreliable model predictions. Though deep learning models achieve remarkable performance on various benchmarks, the study of model calibration and reliability is relatively under-explored. Ideal deep models should have not only high predictive performance but also be well calibrated. There have been some recent advances in calibrating deep models"},"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":"2308.01222","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-02T15:28:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e914b340bf78d2d07e4abc5e5dd67aefc1eeaf1c0c03a05e03a0e2a3b90b4d8c","abstract_canon_sha256":"c6e34651a1e12b9c9e4fcdc1d51751a5e120bb355771826c39fc381878198b12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:11.713019Z","signature_b64":"TmufixVY+vtDTzNxqu/Cs0GaxQh1lA7Fw/+84tCb3NBK7fEgHGxf9WVSbP2d+nlYTuotoPARMbHB31Nfh4l4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41b3849d50ed1c1b7a476ee652ec52e003914fbe00d821440c1763434fd6b17f","last_reissued_at":"2026-07-05T12:11:11.712502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:11.712502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng Wang","submitted_at":"2023-08-02T15:28:10Z","abstract_excerpt":"Calibrating deep neural models plays an important role in building reliable, robust AI systems in safety-critical applications. Recent work has shown that modern neural networks that possess high predictive capability are poorly calibrated and produce unreliable model predictions. Though deep learning models achieve remarkable performance on various benchmarks, the study of model calibration and reliability is relatively under-explored. Ideal deep models should have not only high predictive performance but also be well calibrated. There have been some recent advances in calibrating deep models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01222","kind":"arxiv","version":4},"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/2308.01222/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":"2308.01222","created_at":"2026-07-05T12:11:11.712566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01222v4","created_at":"2026-07-05T12:11:11.712566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01222","created_at":"2026-07-05T12:11:11.712566+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGZYJHKQ5UOB","created_at":"2026-07-05T12:11:11.712566+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGZYJHKQ5UOBW6SH","created_at":"2026-07-05T12:11:11.712566+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGZYJHKQ","created_at":"2026-07-05T12:11:11.712566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07170","citing_title":"PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02671","citing_title":"Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22179","citing_title":"The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20642","citing_title":"Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21060","citing_title":"Divide et Calibra: Multiclass Local Calibration via Vector Quantization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13595","citing_title":"Inducing Artificial Uncertainty in Language Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13627","citing_title":"SINAPSE: A lightweight deep learning framework for accurate and explainable neutron-$\\gamma$ discrimination","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21260","citing_title":"Calibeating Prediction-Powered Inference","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08639","citing_title":"VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19444","citing_title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","ref_index":139,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A","json":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A.json","graph_json":"https://pith.science/api/pith-number/IGZYJHKQ5UOBW6SHN3TFF3CS4A/graph.json","events_json":"https://pith.science/api/pith-number/IGZYJHKQ5UOBW6SHN3TFF3CS4A/events.json","paper":"https://pith.science/paper/IGZYJHKQ"},"agent_actions":{"view_html":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A","download_json":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A.json","view_paper":"https://pith.science/paper/IGZYJHKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01222&json=true","fetch_graph":"https://pith.science/api/pith-number/IGZYJHKQ5UOBW6SHN3TFF3CS4A/graph.json","fetch_events":"https://pith.science/api/pith-number/IGZYJHKQ5UOBW6SHN3TFF3CS4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A/action/storage_attestation","attest_author":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A/action/author_attestation","sign_citation":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A/action/citation_signature","submit_replication":"https://pith.science/pith/IGZYJHKQ5UOBW6SHN3TFF3CS4A/action/replication_record"}},"created_at":"2026-07-05T12:11:11.712566+00:00","updated_at":"2026-07-05T12:11:11.712566+00:00"}