{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:27ZHZPHPWEZDRNAQ2IYLDQKIR6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ca5654433cef013e2a2a49d15bb1d6016ab5e04fe39c08496e302428aa39038f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-16T20:00:08Z","title_canon_sha256":"58fff2751f054edaf32ab216a52e4649c50838d908114914a816357af498a6a3"},"schema_version":"1.0","source":{"id":"2408.08998","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08998","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08998v3","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08998","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"27ZHZPHPWEZD","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"27ZHZPHPWEZDRNAQ","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"27ZHZPHP","created_at":"2026-07-05T11:47:13Z"}],"graph_snapshots":[{"event_id":"sha256:f28f1a860a42d0945b03a3d9b9c59ddfd728a653c63a8a83709cb35cec690a5f","target":"graph","created_at":"2026-07-05T11:47:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.08998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in machine learning have significantly improved prediction accuracy in various applications. However, ensuring the calibration of probabilistic predictions remains a significant challenge. Despite efforts to enhance model calibration, the rigorous statistical evaluation of model calibration remains less explored. In this work, we develop confidence intervals the $\\ell_2$ Expected Calibration Error (ECE). We consider top-1-to-$k$ calibration, which includes both the popular notion of confidence calibration as well as full calibration. For a debiased estimator of the ECE, we show","authors_text":"Edgar Dobriban, Ian J. Barnett, Pratik Chaudhari, Yan Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-16T20:00:08Z","title":"A Confidence Interval for the $\\ell_2$ Expected Calibration Error"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08998","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a30f985b34cd1bb9cff06b43472fdb79ef4a75d7e6e4e14e82b8eece6a750a00","target":"record","created_at":"2026-07-05T11:47:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ca5654433cef013e2a2a49d15bb1d6016ab5e04fe39c08496e302428aa39038f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-16T20:00:08Z","title_canon_sha256":"58fff2751f054edaf32ab216a52e4649c50838d908114914a816357af498a6a3"},"schema_version":"1.0","source":{"id":"2408.08998","kind":"arxiv","version":3}},"canonical_sha256":"d7f27cbcefb13238b410d230b1c1488f9d2c3959c2eb47e2d4c322c8ef5cf90c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7f27cbcefb13238b410d230b1c1488f9d2c3959c2eb47e2d4c322c8ef5cf90c","first_computed_at":"2026-07-05T11:47:13.211673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:13.211673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Ib5eFvK6JqGg91+AcTA99vu3qC2uKyk+Q7dfBFqP2dA0jYbjX56DPNmigM+WEk8Ppw8ZlM3AR5Vwf0gkm0UAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:13.212063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08998","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a30f985b34cd1bb9cff06b43472fdb79ef4a75d7e6e4e14e82b8eece6a750a00","sha256:f28f1a860a42d0945b03a3d9b9c59ddfd728a653c63a8a83709cb35cec690a5f"],"state_sha256":"41bfc787e0106b0b1784df9aa3ad064195e8c7adee8fd371f82adf33a15b5415"}