{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JOW6UEEPZBN6XFAMOMV74QGOSP","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":"0adde1da5590b94cb472222805c76d5d850cd31db3f3c7fc621f7d0ff62e7c5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T11:36:12Z","title_canon_sha256":"30c0e22e49a87d34d9d119ba7d16853f1d110cf88d74dd1b990d90ea03ed71a3"},"schema_version":"1.0","source":{"id":"2404.02655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02655","created_at":"2026-07-05T09:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02655v2","created_at":"2026-07-05T09:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02655","created_at":"2026-07-05T09:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"JOW6UEEPZBN6","created_at":"2026-07-05T09:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"JOW6UEEPZBN6XFAM","created_at":"2026-07-05T09:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"JOW6UEEP","created_at":"2026-07-05T09:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:43f236736831f48c9aef52318142b7f1416c6ba65f24c4db3c6f8775eb4d916f","target":"graph","created_at":"2026-07-05T09:17:39Z","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/2404.02655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless. However, post-alignment, these language models often exhibit overconfidence, where the expressed confidence does not accurately calibrate with their correctness rate. In this paper, we decompose the language model confidence into the \\textit{Uncertainty} about the question and the \\textit{Fidelity} to the answer generated by language models. Then, we propose a plug-and-play method to estimate the confidence of language models. Our method has shown good calibration performance b","authors_text":"Chong Peng, Linsen Guo, Mianqiu Huang, Mozhi Zhang, Peng Yan, Rundong Shi, Xipeng Qiu, Yaqian Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T11:36:12Z","title":"Calibrating the Confidence of Large Language Models by Eliciting Fidelity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02655","kind":"arxiv","version":2},"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":"sha256:2c2d7e2e8c049cad03e6e61cdb33ca05addf43462c161d13bbe040dcca39a233","target":"record","created_at":"2026-07-05T09:17:39Z","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":"0adde1da5590b94cb472222805c76d5d850cd31db3f3c7fc621f7d0ff62e7c5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T11:36:12Z","title_canon_sha256":"30c0e22e49a87d34d9d119ba7d16853f1d110cf88d74dd1b990d90ea03ed71a3"},"schema_version":"1.0","source":{"id":"2404.02655","kind":"arxiv","version":2}},"canonical_sha256":"4badea108fc85beb940c732bfe40ce93e282e52b4c0a76658250f85383e05e81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4badea108fc85beb940c732bfe40ce93e282e52b4c0a76658250f85383e05e81","first_computed_at":"2026-07-05T09:17:39.500658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:39.500658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k6Hgh1eZlrg6fbUXFWPFp2ek1+RxDExi8UjOGLnD2OmX78xAqgWx6+UyQ/uUd3FJDX7uFTwvYE4/GM/VjbVxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:39.501133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c2d7e2e8c049cad03e6e61cdb33ca05addf43462c161d13bbe040dcca39a233","sha256:43f236736831f48c9aef52318142b7f1416c6ba65f24c4db3c6f8775eb4d916f"],"state_sha256":"9c0a75bc4c1f82fd19992fc4e6469f44e6ef3b68f64d57dfd02dd06cc51a5bae"}