{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PB4X3W72MZVPIKW4PK3CTSHTU7","short_pith_number":"pith:PB4X3W72","schema_version":"1.0","canonical_sha256":"78797ddbfa666af42adc7ab629c8f3a7d3a0255d76e6d910c15d13981ac4749f","source":{"kind":"arxiv","id":"2605.30188","version":1},"attestation_state":"computed","paper":{"title":"CalArena: A Large-Scale Post-Hoc Calibration Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Holzm\\\"uller, Eug\\`ene Berta, Francis Bach, Michael I. Jordan","submitted_at":"2026-05-28T16:31:36Z","abstract_excerpt":"Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and widely used solution, but the large number of proposed methods, combined with small-scale and inconsistent evaluations, makes it difficult to determine which approaches are truly effective in practice. We introduce a large-scale, standardized benchmark for post-hoc calibration, covering nearly 2000 experiments across tabular and computer vision tasks, including binary, multiclass, and large-scale classification setting"},"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":"2605.30188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:31:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"68292f4ae1f2df4020a4b6cf901e144450d6bdbe954f63a4218fee9c6f18fde5","abstract_canon_sha256":"297ccb391ef23342c3cc7b8b3c5cebcdd1f6206f52af4f38e5fa940ff2f6a49e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:12.348220Z","signature_b64":"d4VyZCsCOA6NZgAvrgbY2MQw9Mx3y+6/hj/hwM/h6LY+D6iYmESKSBRPmMXUEU9UHzZ4f7I74xqI07yXd5B7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78797ddbfa666af42adc7ab629c8f3a7d3a0255d76e6d910c15d13981ac4749f","last_reissued_at":"2026-05-29T02:06:12.347812Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:12.347812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CalArena: A Large-Scale Post-Hoc Calibration Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Holzm\\\"uller, Eug\\`ene Berta, Francis Bach, Michael I. Jordan","submitted_at":"2026-05-28T16:31:36Z","abstract_excerpt":"Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and widely used solution, but the large number of proposed methods, combined with small-scale and inconsistent evaluations, makes it difficult to determine which approaches are truly effective in practice. We introduce a large-scale, standardized benchmark for post-hoc calibration, covering nearly 2000 experiments across tabular and computer vision tasks, including binary, multiclass, and large-scale classification setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30188","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/2605.30188/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":"2605.30188","created_at":"2026-05-29T02:06:12.347870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30188v1","created_at":"2026-05-29T02:06:12.347870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30188","created_at":"2026-05-29T02:06:12.347870+00:00"},{"alias_kind":"pith_short_12","alias_value":"PB4X3W72MZVP","created_at":"2026-05-29T02:06:12.347870+00:00"},{"alias_kind":"pith_short_16","alias_value":"PB4X3W72MZVPIKW4","created_at":"2026-05-29T02:06:12.347870+00:00"},{"alias_kind":"pith_short_8","alias_value":"PB4X3W72","created_at":"2026-05-29T02:06:12.347870+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/PB4X3W72MZVPIKW4PK3CTSHTU7","json":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7.json","graph_json":"https://pith.science/api/pith-number/PB4X3W72MZVPIKW4PK3CTSHTU7/graph.json","events_json":"https://pith.science/api/pith-number/PB4X3W72MZVPIKW4PK3CTSHTU7/events.json","paper":"https://pith.science/paper/PB4X3W72"},"agent_actions":{"view_html":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7","download_json":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7.json","view_paper":"https://pith.science/paper/PB4X3W72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30188&json=true","fetch_graph":"https://pith.science/api/pith-number/PB4X3W72MZVPIKW4PK3CTSHTU7/graph.json","fetch_events":"https://pith.science/api/pith-number/PB4X3W72MZVPIKW4PK3CTSHTU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7/action/storage_attestation","attest_author":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7/action/author_attestation","sign_citation":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7/action/citation_signature","submit_replication":"https://pith.science/pith/PB4X3W72MZVPIKW4PK3CTSHTU7/action/replication_record"}},"created_at":"2026-05-29T02:06:12.347870+00:00","updated_at":"2026-05-29T02:06:12.347870+00:00"}