{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YF2QJH3GZVWOJC62RECETNC2SU","short_pith_number":"pith:YF2QJH3G","schema_version":"1.0","canonical_sha256":"c175049f66cd6ce48bda890449b45a951536f9c52509ca62c0292897f25e25a3","source":{"kind":"arxiv","id":"2607.20526","version":1},"attestation_state":"computed","paper":{"title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Daniel Yang, Matthew ffrench-Constant, Sanyam Kapoor, Xinmeng Huang","submitted_at":"2026-07-10T01:56:30Z","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"},"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":"2607.20526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T01:56:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"81e12c329ffd6aa0dd82353bfbb34bb19f1abc2907d8e47c4e1d5f3b5641af77","abstract_canon_sha256":"dabf73d1b76d5a2bf42111e07e73297200a9135e6ade7a19c3a40586b16f138e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:20.432081Z","signature_b64":"xfNWBPg9X4yjiltDLD2oduuXoPRNHwgNFpsp2EpRkGTgMxN50cIA83h2YODFu5QwdOoGwGtHMbr/C9uFuaKUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c175049f66cd6ce48bda890449b45a951536f9c52509ca62c0292897f25e25a3","last_reissued_at":"2026-07-24T00:23:20.431244Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:20.431244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Daniel Yang, Matthew ffrench-Constant, Sanyam Kapoor, Xinmeng Huang","submitted_at":"2026-07-10T01:56:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20526","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/2607.20526/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":"2607.20526","created_at":"2026-07-24T00:23:20.431687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20526v1","created_at":"2026-07-24T00:23:20.431687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20526","created_at":"2026-07-24T00:23:20.431687+00:00"},{"alias_kind":"pith_short_12","alias_value":"YF2QJH3GZVWO","created_at":"2026-07-24T00:23:20.431687+00:00"},{"alias_kind":"pith_short_16","alias_value":"YF2QJH3GZVWOJC62","created_at":"2026-07-24T00:23:20.431687+00:00"},{"alias_kind":"pith_short_8","alias_value":"YF2QJH3G","created_at":"2026-07-24T00:23:20.431687+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/YF2QJH3GZVWOJC62RECETNC2SU","json":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU.json","graph_json":"https://pith.science/api/pith-number/YF2QJH3GZVWOJC62RECETNC2SU/graph.json","events_json":"https://pith.science/api/pith-number/YF2QJH3GZVWOJC62RECETNC2SU/events.json","paper":"https://pith.science/paper/YF2QJH3G"},"agent_actions":{"view_html":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU","download_json":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU.json","view_paper":"https://pith.science/paper/YF2QJH3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20526&json=true","fetch_graph":"https://pith.science/api/pith-number/YF2QJH3GZVWOJC62RECETNC2SU/graph.json","fetch_events":"https://pith.science/api/pith-number/YF2QJH3GZVWOJC62RECETNC2SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU/action/storage_attestation","attest_author":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU/action/author_attestation","sign_citation":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU/action/citation_signature","submit_replication":"https://pith.science/pith/YF2QJH3GZVWOJC62RECETNC2SU/action/replication_record"}},"created_at":"2026-07-24T00:23:20.431687+00:00","updated_at":"2026-07-24T00:23:20.431687+00:00"}