{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5APEOBXOIM6SLX375T4CI53TDT","short_pith_number":"pith:5APEOBXO","canonical_record":{"source":{"id":"2412.15296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T10:04:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e11494b003022ccc2ea50f4e0d17dc7107ca784444dd62cef0ca7dc11ae9fb59","abstract_canon_sha256":"b475ecf7dc98a60cd2da9fee2e14f948258c8eed907c919b25b2bb234da3193e"},"schema_version":"1.0"},"canonical_sha256":"e81e4706ee433d25df7fecf82477731cd3fca0c74f5a444926f3833f435fdec6","source":{"kind":"arxiv","id":"2412.15296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15296","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15296v1","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15296","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"5APEOBXOIM6S","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"pith_short_16","alias_value":"5APEOBXOIM6SLX37","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"pith_short_8","alias_value":"5APEOBXO","created_at":"2026-07-05T09:52:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5APEOBXOIM6SLX375T4CI53TDT","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T10:04:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e11494b003022ccc2ea50f4e0d17dc7107ca784444dd62cef0ca7dc11ae9fb59","abstract_canon_sha256":"b475ecf7dc98a60cd2da9fee2e14f948258c8eed907c919b25b2bb234da3193e"},"schema_version":"1.0"},"canonical_sha256":"e81e4706ee433d25df7fecf82477731cd3fca0c74f5a444926f3833f435fdec6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:20.849384Z","signature_b64":"71M9ZVzoMR4hqK7D/rsgQ7N3sS7zbUtz5uBy2j4A4f4n9hQpRZd485idoL9dMo3GUqs9AUOsu5eznVzv4tBtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e81e4706ee433d25df7fecf82477731cd3fca0c74f5a444926f3833f435fdec6","last_reissued_at":"2026-07-05T09:52:20.848863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:20.848863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15296","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+e+/7SzzUpxJNT4nLh5+HEyS5JIBtqkHIU32Xwmey46GISTmc6shMdaRtSzFymtalQh7moFcxFXUgiLzh8TDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:56:21.901630Z"},"content_sha256":"f49bb5e0820bdf9a912609bc29ac435477cc21636394347c9694ea4c71768923","schema_version":"1.0","event_id":"sha256:f49bb5e0820bdf9a912609bc29ac435477cc21636394347c9694ea4c71768923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5APEOBXOIM6SLX375T4CI53TDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confidence in the Reasoning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chris Holmes, Yudi Pawitan","submitted_at":"2024-12-19T10:04:29Z","abstract_excerpt":"There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it correlates with accuracy. Confidence is measured (i) qualitatively in terms of persistence in keeping their answer when prompted to reconsider, and (ii) quantitatively in terms of self-reported confidence score. We investigate the performance of three LLMs -- GPT4o, GPT4-turbo and Mistral -- on two benchmark sets of questions on causal judgement and formal f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15296","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/2412.15296/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OwArPnCLi8G/3aKVmvw0UVF6ijlKDJ2v00oiv7OECJqbnjNnLj2y4Hm+7afq4uGCFwWFAwuer9bOVG+DWMScBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:56:21.902374Z"},"content_sha256":"9b95c464efbda24aa3c03660ab37c4e0717c3118847142d734aeff8c8d684759","schema_version":"1.0","event_id":"sha256:9b95c464efbda24aa3c03660ab37c4e0717c3118847142d734aeff8c8d684759"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5APEOBXOIM6SLX375T4CI53TDT/bundle.json","state_url":"https://pith.science/pith/5APEOBXOIM6SLX375T4CI53TDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5APEOBXOIM6SLX375T4CI53TDT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T15:56:21Z","links":{"resolver":"https://pith.science/pith/5APEOBXOIM6SLX375T4CI53TDT","bundle":"https://pith.science/pith/5APEOBXOIM6SLX375T4CI53TDT/bundle.json","state":"https://pith.science/pith/5APEOBXOIM6SLX375T4CI53TDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5APEOBXOIM6SLX375T4CI53TDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5APEOBXOIM6SLX375T4CI53TDT","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":"b475ecf7dc98a60cd2da9fee2e14f948258c8eed907c919b25b2bb234da3193e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T10:04:29Z","title_canon_sha256":"e11494b003022ccc2ea50f4e0d17dc7107ca784444dd62cef0ca7dc11ae9fb59"},"schema_version":"1.0","source":{"id":"2412.15296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15296","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15296v1","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15296","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"5APEOBXOIM6S","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"pith_short_16","alias_value":"5APEOBXOIM6SLX37","created_at":"2026-07-05T09:52:20Z"},{"alias_kind":"pith_short_8","alias_value":"5APEOBXO","created_at":"2026-07-05T09:52:20Z"}],"graph_snapshots":[{"event_id":"sha256:9b95c464efbda24aa3c03660ab37c4e0717c3118847142d734aeff8c8d684759","target":"graph","created_at":"2026-07-05T09:52:20Z","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/2412.15296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it correlates with accuracy. Confidence is measured (i) qualitatively in terms of persistence in keeping their answer when prompted to reconsider, and (ii) quantitatively in terms of self-reported confidence score. We investigate the performance of three LLMs -- GPT4o, GPT4-turbo and Mistral -- on two benchmark sets of questions on causal judgement and formal f","authors_text":"Chris Holmes, Yudi Pawitan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T10:04:29Z","title":"Confidence in the Reasoning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15296","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:f49bb5e0820bdf9a912609bc29ac435477cc21636394347c9694ea4c71768923","target":"record","created_at":"2026-07-05T09:52:20Z","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":"b475ecf7dc98a60cd2da9fee2e14f948258c8eed907c919b25b2bb234da3193e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T10:04:29Z","title_canon_sha256":"e11494b003022ccc2ea50f4e0d17dc7107ca784444dd62cef0ca7dc11ae9fb59"},"schema_version":"1.0","source":{"id":"2412.15296","kind":"arxiv","version":1}},"canonical_sha256":"e81e4706ee433d25df7fecf82477731cd3fca0c74f5a444926f3833f435fdec6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e81e4706ee433d25df7fecf82477731cd3fca0c74f5a444926f3833f435fdec6","first_computed_at":"2026-07-05T09:52:20.848863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:20.848863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"71M9ZVzoMR4hqK7D/rsgQ7N3sS7zbUtz5uBy2j4A4f4n9hQpRZd485idoL9dMo3GUqs9AUOsu5eznVzv4tBtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:20.849384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f49bb5e0820bdf9a912609bc29ac435477cc21636394347c9694ea4c71768923","sha256:9b95c464efbda24aa3c03660ab37c4e0717c3118847142d734aeff8c8d684759"],"state_sha256":"963c38aa5e00f7405f61eb2a88b7ebb07803378ee32b33bd504151f960175e07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o5XaAv06x48+dFqs/LyWsyeNN0B4amC3XI24IHER47PMA5RRIrR+DtGEZ9RjyDOld+XbIm2vOunoFxWyMkAlBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:56:21.939037Z","bundle_sha256":"2fd0c79152c4a883d415fe23f899cf10dc337cd64c1b7dbb48aa6d8972646940"}}