{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4EMWEVCSSDQABUBMZ6EX6E6OEP","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":"5a2b857394929a0aa49ddc40af71e617aa11b7b133aa9441253f35b506537338","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:42:04Z","title_canon_sha256":"fa2f6b752e0b2d49d6097237f0d6a6c50b93d21919a6933015f43b53b5dcf1ec"},"schema_version":"1.0","source":{"id":"2405.16282","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16282","created_at":"2026-07-05T08:32:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16282v5","created_at":"2026-07-05T08:32:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16282","created_at":"2026-07-05T08:32:12Z"},{"alias_kind":"pith_short_12","alias_value":"4EMWEVCSSDQA","created_at":"2026-07-05T08:32:12Z"},{"alias_kind":"pith_short_16","alias_value":"4EMWEVCSSDQABUBM","created_at":"2026-07-05T08:32:12Z"},{"alias_kind":"pith_short_8","alias_value":"4EMWEVCS","created_at":"2026-07-05T08:32:12Z"}],"graph_snapshots":[{"event_id":"sha256:883bbe98546c3416937805c50059c5dbc0481045a7565c05e65638d32f3f6e29","target":"graph","created_at":"2026-07-05T08:32:12Z","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/2405.16282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the use of Large Language Models (LLMs) becomes more widespread, understanding their self-evaluation of confidence in generated responses becomes increasingly important as it is integral to the reliability of the output of these models. We introduce the concept of Confidence-Probability Alignment, that connects an LLM's internal confidence, quantified by token probabilities, to the confidence conveyed in the model's response when explicitly asked about its certainty. Using various datasets and prompting techniques that encourage model introspection, we probe the alignment between models' in","authors_text":"Abhishek Kumar, Ali Emami, Jad Kabbara, Robert Morabito, Sanzhar Umbet","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:42:04Z","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16282","kind":"arxiv","version":5},"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:b7f90c6fb61e6421e4d221406d4e9adc2206468d6685784e8165d43b03c68411","target":"record","created_at":"2026-07-05T08:32:12Z","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":"5a2b857394929a0aa49ddc40af71e617aa11b7b133aa9441253f35b506537338","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:42:04Z","title_canon_sha256":"fa2f6b752e0b2d49d6097237f0d6a6c50b93d21919a6933015f43b53b5dcf1ec"},"schema_version":"1.0","source":{"id":"2405.16282","kind":"arxiv","version":5}},"canonical_sha256":"e11962545290e000d02ccf897f13ce23f57a1aaa0dc1e2cb952398845f780d5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e11962545290e000d02ccf897f13ce23f57a1aaa0dc1e2cb952398845f780d5f","first_computed_at":"2026-07-05T08:32:12.919724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:12.919724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ze8712qGYFvOayI4rWruzEE9ZaUZWi5M5F3N5wxKK5djSyPa4R1CvwS7s9DbMsApiYTg+AM5nAeNaLgxVLzvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:12.920111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16282","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7f90c6fb61e6421e4d221406d4e9adc2206468d6685784e8165d43b03c68411","sha256:883bbe98546c3416937805c50059c5dbc0481045a7565c05e65638d32f3f6e29"],"state_sha256":"fb147d99e0395391081c9eeaa46cf7aebcb654b40b6ac8667abb4a8b28cc5a29"}