{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZKY3Y6KVCREMBWR2AAEZ22MOYY","short_pith_number":"pith:ZKY3Y6KV","canonical_record":{"source":{"id":"2505.19073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T10:17:57Z","cross_cats_sorted":[],"title_canon_sha256":"4c73e52f94e969b152c936608f72104b335af9e3db1b37c3d7544075a31e5a8f","abstract_canon_sha256":"967c827efebc8f0fe0e10976c1afa87dc88cf15271f1c804249da483164532b9"},"schema_version":"1.0"},"canonical_sha256":"cab1bc79551448c0da3a00099d698ec61d79d652829260b1dfe63df5e8b071fb","source":{"kind":"arxiv","id":"2505.19073","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19073","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19073v2","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19073","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZKY3Y6KVCREM","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZKY3Y6KVCREMBWR2","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZKY3Y6KV","created_at":"2026-07-05T11:39:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZKY3Y6KVCREMBWR2AAEZ22MOYY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T10:17:57Z","cross_cats_sorted":[],"title_canon_sha256":"4c73e52f94e969b152c936608f72104b335af9e3db1b37c3d7544075a31e5a8f","abstract_canon_sha256":"967c827efebc8f0fe0e10976c1afa87dc88cf15271f1c804249da483164532b9"},"schema_version":"1.0"},"canonical_sha256":"cab1bc79551448c0da3a00099d698ec61d79d652829260b1dfe63df5e8b071fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:54.250667Z","signature_b64":"x7E1k/0xDPoAM2DRMTX4auTAJ1z+ht8ZmmgaeRTtnuhBjchOyRyQKhvAq5/DsjLDh833s25crjKNmtUfpk65AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab1bc79551448c0da3a00099d698ec61d79d652829260b1dfe63df5e8b071fb","last_reissued_at":"2026-07-05T11:39:54.250121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:54.250121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19073","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJpFOXYJ393FQrhdCes+U2nMXIKw5Qik6Kns43eZC4m2FURc6glVHpP4jya3VBHWaWI5ROA/jM9P9idY8hr5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:37:35.261514Z"},"content_sha256":"adee08550cc48b6bd92741a323525bc8f3d45ab4dc72a517ac5bd17213aa3339","schema_version":"1.0","event_id":"sha256:adee08550cc48b6bd92741a323525bc8f3d45ab4dc72a517ac5bd17213aa3339"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZKY3Y6KVCREMBWR2AAEZ22MOYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Harmonized Uncertainty Estimation for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heming Xia, Jing Long, Lei Sha, Muge Qi, Peiyi Wang, Rui Li, Zhifang Sui","submitted_at":"2025-05-25T10:17:57Z","abstract_excerpt":"To facilitate robust and trustworthy deployment of large language models (LLMs), it is essential to quantify the reliability of their generations through uncertainty estimation. While recent efforts have made significant advancements by leveraging the internal logic and linguistic features of LLMs to estimate uncertainty scores, our empirical analysis highlights the pitfalls of these methods to strike a harmonized estimation between indication, balance, and calibration, which hinders their broader capability for accurate uncertainty estimation. To address this challenge, we propose CUE (Correc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19073","kind":"arxiv","version":2},"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/2505.19073/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":"2026-07-05T11:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGJzRN0DEQQPuA5WSFouwgVVUOcBhYnqSpMbjonYH6eMjqaO2kyOoVT8emcrEJcHK9IT550yTBkvYNb52HSCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:37:35.262020Z"},"content_sha256":"f74f428f5a6dc3c2906a7a9f3c7a7f9df5c5d3eef6717c3a0145eb72dd80f735","schema_version":"1.0","event_id":"sha256:f74f428f5a6dc3c2906a7a9f3c7a7f9df5c5d3eef6717c3a0145eb72dd80f735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY/bundle.json","state_url":"https://pith.science/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY/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":"2026-08-07T22:37:35Z","links":{"resolver":"https://pith.science/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY","bundle":"https://pith.science/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY/bundle.json","state":"https://pith.science/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKY3Y6KVCREMBWR2AAEZ22MOYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZKY3Y6KVCREMBWR2AAEZ22MOYY","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":"967c827efebc8f0fe0e10976c1afa87dc88cf15271f1c804249da483164532b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T10:17:57Z","title_canon_sha256":"4c73e52f94e969b152c936608f72104b335af9e3db1b37c3d7544075a31e5a8f"},"schema_version":"1.0","source":{"id":"2505.19073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19073","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19073v2","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19073","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZKY3Y6KVCREM","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZKY3Y6KVCREMBWR2","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZKY3Y6KV","created_at":"2026-07-05T11:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:f74f428f5a6dc3c2906a7a9f3c7a7f9df5c5d3eef6717c3a0145eb72dd80f735","target":"graph","created_at":"2026-07-05T11:39:54Z","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/2505.19073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To facilitate robust and trustworthy deployment of large language models (LLMs), it is essential to quantify the reliability of their generations through uncertainty estimation. While recent efforts have made significant advancements by leveraging the internal logic and linguistic features of LLMs to estimate uncertainty scores, our empirical analysis highlights the pitfalls of these methods to strike a harmonized estimation between indication, balance, and calibration, which hinders their broader capability for accurate uncertainty estimation. To address this challenge, we propose CUE (Correc","authors_text":"Heming Xia, Jing Long, Lei Sha, Muge Qi, Peiyi Wang, Rui Li, Zhifang Sui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T10:17:57Z","title":"Towards Harmonized Uncertainty Estimation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19073","kind":"arxiv","version":2},"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:adee08550cc48b6bd92741a323525bc8f3d45ab4dc72a517ac5bd17213aa3339","target":"record","created_at":"2026-07-05T11:39:54Z","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":"967c827efebc8f0fe0e10976c1afa87dc88cf15271f1c804249da483164532b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T10:17:57Z","title_canon_sha256":"4c73e52f94e969b152c936608f72104b335af9e3db1b37c3d7544075a31e5a8f"},"schema_version":"1.0","source":{"id":"2505.19073","kind":"arxiv","version":2}},"canonical_sha256":"cab1bc79551448c0da3a00099d698ec61d79d652829260b1dfe63df5e8b071fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab1bc79551448c0da3a00099d698ec61d79d652829260b1dfe63df5e8b071fb","first_computed_at":"2026-07-05T11:39:54.250121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:54.250121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x7E1k/0xDPoAM2DRMTX4auTAJ1z+ht8ZmmgaeRTtnuhBjchOyRyQKhvAq5/DsjLDh833s25crjKNmtUfpk65AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:54.250667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adee08550cc48b6bd92741a323525bc8f3d45ab4dc72a517ac5bd17213aa3339","sha256:f74f428f5a6dc3c2906a7a9f3c7a7f9df5c5d3eef6717c3a0145eb72dd80f735"],"state_sha256":"62349696ae2a3396e6cfaea97d70ca89bc08c820afeb80478ebb095d53153ae1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9MoCD9+6uikKPuyGCD6iDv77sJPufkc8nTpBNSJBLCppzIoXtsPGPChrFgmTZZdrTLJue4ECIj6XfnQ3+pHBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:37:35.267469Z","bundle_sha256":"d508cac2c7edfc8ea9e6f6c8293593b3095d76e7222aa66e6ba95f0e8dd74a37"}}