{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CM6U2UR3FGDDSHFWFDDE7FR5FV","short_pith_number":"pith:CM6U2UR3","canonical_record":{"source":{"id":"2505.23854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T02:04:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"22e72412526b29032dd4cccc5aa19cb5294f860803678ab175acdc5f733101ce","abstract_canon_sha256":"b5476024c125091a037cb67640cbf68b8e106d100492e0c238d8f342653f88e9"},"schema_version":"1.0"},"canonical_sha256":"133d4d523b2986391cb628c64f963d2d402feb6dbccbc342ef6ee38384a56a9b","source":{"kind":"arxiv","id":"2505.23854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23854","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23854v1","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23854","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"CM6U2UR3FGDD","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"CM6U2UR3FGDDSHFW","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"CM6U2UR3","created_at":"2026-07-05T11:12:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CM6U2UR3FGDDSHFWFDDE7FR5FV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T02:04:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"22e72412526b29032dd4cccc5aa19cb5294f860803678ab175acdc5f733101ce","abstract_canon_sha256":"b5476024c125091a037cb67640cbf68b8e106d100492e0c238d8f342653f88e9"},"schema_version":"1.0"},"canonical_sha256":"133d4d523b2986391cb628c64f963d2d402feb6dbccbc342ef6ee38384a56a9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:36.798048Z","signature_b64":"U8xaNflbn94GYjoWITunA6kPGAL1e230GrzQA4NcOUKm2jdZXXHtGmzzkvE+SNRinrayUa5NMyVSwnXdUYxzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"133d4d523b2986391cb628c64f963d2d402feb6dbccbc342ef6ee38384a56a9b","last_reissued_at":"2026-07-05T11:12:36.797464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:36.797464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23854","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":"2026-07-05T11:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBMX8YcCjV+dH4mmAp5lfCS2ddNkd8nX+iWHIUvDGOJ0IruIZAPPqB3KmYLPq2hriCcYlpETlyNl+zxsuSfACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:31:01.495130Z"},"content_sha256":"d6e52ef67a3a424bdc52f6564919c20d6753a70214d138ef9617ac4cd9599b48","schema_version":"1.0","event_id":"sha256:d6e52ef67a3a424bdc52f6564919c20d6753a70214d138ef9617ac4cd9599b48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CM6U2UR3FGDDSHFWFDDE7FR5FV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chang Xu, Linwei Tao, Minjing Dong, Philip Torr, Tao Huang, Yi-Fan Yeh","submitted_at":"2025-05-29T02:04:49Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed in high-stakes applications, robust uncertainty estimation is essential for ensuring the safe and trustworthy deployment of LLMs. We present the most comprehensive study to date of uncertainty estimation in LLMs, evaluating 80 models spanning open- and closed-source families, dense and Mixture-of-Experts (MoE) architectures, reasoning and non-reasoning modes, quantization variants and parameter scales from 0.6B to 671B. Focusing on three representative black-box single-pass methods, including token probability-based uncertainty (TPU), n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23854","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/2505.23854/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":"2026-07-05T11:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRZSXg/Hw+SrT1gOgEEaFARkWB37JcaJH4+DUjELQLzwjnOE4KmGH9nWlS2Q6M01B+Qdr8zqMSgIBY/j/w99Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:31:01.495939Z"},"content_sha256":"87a36eed8e3b3918b6a88d82e20c743e69d755f84d10430cd3ec8970565911b1","schema_version":"1.0","event_id":"sha256:87a36eed8e3b3918b6a88d82e20c743e69d755f84d10430cd3ec8970565911b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV/bundle.json","state_url":"https://pith.science/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV/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":"2026-08-05T16:31:01Z","links":{"resolver":"https://pith.science/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV","bundle":"https://pith.science/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV/bundle.json","state":"https://pith.science/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CM6U2UR3FGDDSHFWFDDE7FR5FV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CM6U2UR3FGDDSHFWFDDE7FR5FV","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":"b5476024c125091a037cb67640cbf68b8e106d100492e0c238d8f342653f88e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T02:04:49Z","title_canon_sha256":"22e72412526b29032dd4cccc5aa19cb5294f860803678ab175acdc5f733101ce"},"schema_version":"1.0","source":{"id":"2505.23854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23854","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23854v1","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23854","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"CM6U2UR3FGDD","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"CM6U2UR3FGDDSHFW","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"CM6U2UR3","created_at":"2026-07-05T11:12:36Z"}],"graph_snapshots":[{"event_id":"sha256:87a36eed8e3b3918b6a88d82e20c743e69d755f84d10430cd3ec8970565911b1","target":"graph","created_at":"2026-07-05T11:12:36Z","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/2505.23854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) are increasingly deployed in high-stakes applications, robust uncertainty estimation is essential for ensuring the safe and trustworthy deployment of LLMs. We present the most comprehensive study to date of uncertainty estimation in LLMs, evaluating 80 models spanning open- and closed-source families, dense and Mixture-of-Experts (MoE) architectures, reasoning and non-reasoning modes, quantization variants and parameter scales from 0.6B to 671B. Focusing on three representative black-box single-pass methods, including token probability-based uncertainty (TPU), n","authors_text":"Chang Xu, Linwei Tao, Minjing Dong, Philip Torr, Tao Huang, Yi-Fan Yeh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T02:04:49Z","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23854","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:d6e52ef67a3a424bdc52f6564919c20d6753a70214d138ef9617ac4cd9599b48","target":"record","created_at":"2026-07-05T11:12:36Z","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":"b5476024c125091a037cb67640cbf68b8e106d100492e0c238d8f342653f88e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T02:04:49Z","title_canon_sha256":"22e72412526b29032dd4cccc5aa19cb5294f860803678ab175acdc5f733101ce"},"schema_version":"1.0","source":{"id":"2505.23854","kind":"arxiv","version":1}},"canonical_sha256":"133d4d523b2986391cb628c64f963d2d402feb6dbccbc342ef6ee38384a56a9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"133d4d523b2986391cb628c64f963d2d402feb6dbccbc342ef6ee38384a56a9b","first_computed_at":"2026-07-05T11:12:36.797464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:36.797464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U8xaNflbn94GYjoWITunA6kPGAL1e230GrzQA4NcOUKm2jdZXXHtGmzzkvE+SNRinrayUa5NMyVSwnXdUYxzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:36.798048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6e52ef67a3a424bdc52f6564919c20d6753a70214d138ef9617ac4cd9599b48","sha256:87a36eed8e3b3918b6a88d82e20c743e69d755f84d10430cd3ec8970565911b1"],"state_sha256":"b6dde5fd103b760d20825316ba172a2a1bbbdac5f3f82b5b99aee203033a1555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eyunc0/FKpVveC5002XDYF4fEGYS9Y4VeeUwekYHcXVQa7a2DX22meS0APctTx4qOZEXs6VqkAFg7coHL1qYDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:31:01.517587Z","bundle_sha256":"b8c17b4ccd89d55eb44b3ee7cf503a13246b848b11781cdbd9db9aada5d6dbd0"}}