{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YF2QJH3GZVWOJC62RECETNC2SU","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":"dabf73d1b76d5a2bf42111e07e73297200a9135e6ade7a19c3a40586b16f138e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T01:56:30Z","title_canon_sha256":"81e12c329ffd6aa0dd82353bfbb34bb19f1abc2907d8e47c4e1d5f3b5641af77"},"schema_version":"1.0","source":{"id":"2607.20526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20526","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20526v1","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20526","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"YF2QJH3GZVWO","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"YF2QJH3GZVWOJC62","created_at":"2026-07-24T00:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"YF2QJH3G","created_at":"2026-07-24T00:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:ba289b7be47c31a3935f7f639b4c48b38a99131c62aecbeaae243f948bea5310","target":"graph","created_at":"2026-07-24T00:23:20Z","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/2607.20526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy alone is insufficient: models must also know when they are likely to be wrong. We present ConfidenceBench, a calibration benchmark that evaluates verbalized confidence estimates in 15 frontier LLMs using the Brier score, a proper scoring rule that incentivises truthful probability reporting. Confidence is elicited via prompting, requiring no access to model logits and making the framework applicable to both closed-source and open-source systems. The b","authors_text":"Daniel Yang, Matthew ffrench-Constant, Sanyam Kapoor, Xinmeng Huang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T01:56:30Z","title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20526","kind":"arxiv","version":1},"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":"sha256:9ec456cd16fc205219335207969e22cf900d09c464c6993634e06e23b51ac5eb","target":"record","created_at":"2026-07-24T00:23:20Z","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":"dabf73d1b76d5a2bf42111e07e73297200a9135e6ade7a19c3a40586b16f138e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T01:56:30Z","title_canon_sha256":"81e12c329ffd6aa0dd82353bfbb34bb19f1abc2907d8e47c4e1d5f3b5641af77"},"schema_version":"1.0","source":{"id":"2607.20526","kind":"arxiv","version":1}},"canonical_sha256":"c175049f66cd6ce48bda890449b45a951536f9c52509ca62c0292897f25e25a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c175049f66cd6ce48bda890449b45a951536f9c52509ca62c0292897f25e25a3","first_computed_at":"2026-07-24T00:23:20.431244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:20.431244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xfNWBPg9X4yjiltDLD2oduuXoPRNHwgNFpsp2EpRkGTgMxN50cIA83h2YODFu5QwdOoGwGtHMbr/C9uFuaKUAg==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:20.432081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ec456cd16fc205219335207969e22cf900d09c464c6993634e06e23b51ac5eb","sha256:ba289b7be47c31a3935f7f639b4c48b38a99131c62aecbeaae243f948bea5310"],"state_sha256":"b8e17055582cdeee2eb87614f6abd6e8c442bcacb015295b6ff79e72020734d0"}