{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A2LUKVPYSQJ52B4224FMYT3MZZ","short_pith_number":"pith:A2LUKVPY","schema_version":"1.0","canonical_sha256":"06974555f89413dd079ad70acc4f6cce7d1e233102d6d9d476eb1c49b1962a9f","source":{"kind":"arxiv","id":"2404.13503","version":5},"attestation_state":"computed","paper":{"title":"Calibration Error for Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lunjia Hu, Yifan Wu","submitted_at":"2024-04-21T01:53:20Z","abstract_excerpt":"Calibration allows predictions to be reliably interpreted as probabilities by decision makers. We propose a decision-theoretic calibration error, the Calibration Decision Loss (CDL), defined as the maximum improvement in decision payoff obtained by calibrating the predictions, where the maximum is over all payoff-bounded decision tasks. Vanishing CDL guarantees the payoff loss from miscalibration vanishes simultaneously for all downstream decision tasks. We show separations between CDL and existing calibration error metrics, including the most well-studied metric Expected Calibration Error (EC"},"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":"2404.13503","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T01:53:20Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"eba322f54541ce5b5f804049884758d77b84eeb7515e11809aaf278e3c82d681","abstract_canon_sha256":"5e7c45f903be8f858623bbbf23f8222a8cb8bef59ec8163c1f4308d1855b2e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:52.354135Z","signature_b64":"hv8KA9/8M9ImE0sf9ysezMQ+PSSyfk5cGHWP4sz3BiwcSB9Us2vV8DNg5Pta6MAo+LnltlzkV5Xi5hg6i+l8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06974555f89413dd079ad70acc4f6cce7d1e233102d6d9d476eb1c49b1962a9f","last_reissued_at":"2026-07-05T09:18:52.353663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:52.353663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibration Error for Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lunjia Hu, Yifan Wu","submitted_at":"2024-04-21T01:53:20Z","abstract_excerpt":"Calibration allows predictions to be reliably interpreted as probabilities by decision makers. We propose a decision-theoretic calibration error, the Calibration Decision Loss (CDL), defined as the maximum improvement in decision payoff obtained by calibrating the predictions, where the maximum is over all payoff-bounded decision tasks. Vanishing CDL guarantees the payoff loss from miscalibration vanishes simultaneously for all downstream decision tasks. We show separations between CDL and existing calibration error metrics, including the most well-studied metric Expected Calibration Error (EC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13503","kind":"arxiv","version":5},"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/2404.13503/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":"2404.13503","created_at":"2026-07-05T09:18:52.353719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13503v5","created_at":"2026-07-05T09:18:52.353719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13503","created_at":"2026-07-05T09:18:52.353719+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2LUKVPYSQJ5","created_at":"2026-07-05T09:18:52.353719+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2LUKVPYSQJ52B42","created_at":"2026-07-05T09:18:52.353719+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2LUKVPY","created_at":"2026-07-05T09:18:52.353719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26990","citing_title":"Decision-Aligned Evaluation of Uncertainty Quantification","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18527","citing_title":"Toward Simultaneously Optimal Regret in U-Calibration","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11490","citing_title":"Adaptive Calibration in Non-Stationary Environments","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23017","citing_title":"Smoothed Elicitation Complexity for Approximate $\\Gamma$-calibration of Discrete Classification Tasks","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11490","citing_title":"Adaptive Calibration in Non-Stationary Environments","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10202","citing_title":"Task-Aware Calibration: Provably Optimal Decoding in LLMs","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ","json":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ.json","graph_json":"https://pith.science/api/pith-number/A2LUKVPYSQJ52B4224FMYT3MZZ/graph.json","events_json":"https://pith.science/api/pith-number/A2LUKVPYSQJ52B4224FMYT3MZZ/events.json","paper":"https://pith.science/paper/A2LUKVPY"},"agent_actions":{"view_html":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ","download_json":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ.json","view_paper":"https://pith.science/paper/A2LUKVPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13503&json=true","fetch_graph":"https://pith.science/api/pith-number/A2LUKVPYSQJ52B4224FMYT3MZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/A2LUKVPYSQJ52B4224FMYT3MZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ/action/storage_attestation","attest_author":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ/action/author_attestation","sign_citation":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ/action/citation_signature","submit_replication":"https://pith.science/pith/A2LUKVPYSQJ52B4224FMYT3MZZ/action/replication_record"}},"created_at":"2026-07-05T09:18:52.353719+00:00","updated_at":"2026-07-05T09:18:52.353719+00:00"}