{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WDIO6HIZG3NBWGPBFV5TVPVZEJ","short_pith_number":"pith:WDIO6HIZ","schema_version":"1.0","canonical_sha256":"b0d0ef1d1936da1b19e12d7b3abeb9225ac030528d8541cb930ad8c7353bd423","source":{"kind":"arxiv","id":"2504.15615","version":1},"attestation_state":"computed","paper":{"title":"Dimension-Free Decision Calibration for Nonlinear Loss Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiahao Zhang, Jiayun Wu, Jingwu Tang, Zhiwei Steven Wu","submitted_at":"2025-04-22T06:14:23Z","abstract_excerpt":"When model predictions inform downstream decision making, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. Calibration suffices to guarantee that simple best-response to predictions is optimal. However, calibration for high-dimensional prediction outcome spaces requires exponential computational and statistical complexity. The recent relaxation known as decision calibration ensures the optimality of the simple best-response rule while requiring only polynomial sample complexity in the dimension of outcomes."},"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":"2504.15615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T06:14:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9c621ccba408c43a0681dc8d4e6441b3abb83cc2553680c4eaebcd37284574ee","abstract_canon_sha256":"a4ab2d3f3c8bc721a0a2b0956a545ac6330fd9cc0e717fe185cd2f5da384f52d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:27.438236Z","signature_b64":"N8eOuCkCbzXrNDUKXA7ziqwh8/DWyQIuLZ1hO95wgHN8lOmRFvA5wTQJRM3i+YCaIFO/7w5ErDKK9Q3BlJ7rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0d0ef1d1936da1b19e12d7b3abeb9225ac030528d8541cb930ad8c7353bd423","last_reissued_at":"2026-07-05T10:52:27.437730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:27.437730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimension-Free Decision Calibration for Nonlinear Loss Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiahao Zhang, Jiayun Wu, Jingwu Tang, Zhiwei Steven Wu","submitted_at":"2025-04-22T06:14:23Z","abstract_excerpt":"When model predictions inform downstream decision making, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. Calibration suffices to guarantee that simple best-response to predictions is optimal. However, calibration for high-dimensional prediction outcome spaces requires exponential computational and statistical complexity. The recent relaxation known as decision calibration ensures the optimality of the simple best-response rule while requiring only polynomial sample complexity in the dimension of outcomes."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15615","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/2504.15615/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":"2504.15615","created_at":"2026-07-05T10:52:27.437799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15615v1","created_at":"2026-07-05T10:52:27.437799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15615","created_at":"2026-07-05T10:52:27.437799+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDIO6HIZG3NB","created_at":"2026-07-05T10:52:27.437799+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDIO6HIZG3NBWGPB","created_at":"2026-07-05T10:52:27.437799+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDIO6HIZ","created_at":"2026-07-05T10:52:27.437799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20885","citing_title":"Improved Bounds for Swap Multicalibration and Swap Omniprediction","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ","json":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ.json","graph_json":"https://pith.science/api/pith-number/WDIO6HIZG3NBWGPBFV5TVPVZEJ/graph.json","events_json":"https://pith.science/api/pith-number/WDIO6HIZG3NBWGPBFV5TVPVZEJ/events.json","paper":"https://pith.science/paper/WDIO6HIZ"},"agent_actions":{"view_html":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ","download_json":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ.json","view_paper":"https://pith.science/paper/WDIO6HIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15615&json=true","fetch_graph":"https://pith.science/api/pith-number/WDIO6HIZG3NBWGPBFV5TVPVZEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WDIO6HIZG3NBWGPBFV5TVPVZEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ/action/storage_attestation","attest_author":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ/action/author_attestation","sign_citation":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ/action/citation_signature","submit_replication":"https://pith.science/pith/WDIO6HIZG3NBWGPBFV5TVPVZEJ/action/replication_record"}},"created_at":"2026-07-05T10:52:27.437799+00:00","updated_at":"2026-07-05T10:52:27.437799+00:00"}