{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WZGH7KVT6XX62GOTWDIFWG6UTC","short_pith_number":"pith:WZGH7KVT","canonical_record":{"source":{"id":"2406.12784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"16fbb343c0d6fb9acbe6a6fabf12d5f8f7e800e9148874bbf841519d025326e6","abstract_canon_sha256":"4d6ae1375798cbcf264b7e77643becf69693e34f69d4f7f4514ac4756ee8c225"},"schema_version":"1.0"},"canonical_sha256":"b64c7faab3f5efed19d3b0d05b1bd49895ad2ec21b6a277eb4952620519b3538","source":{"kind":"arxiv","id":"2406.12784","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12784v2","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"WZGH7KVT6XX6","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"WZGH7KVT6XX62GOT","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"WZGH7KVT","created_at":"2026-07-05T11:15:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WZGH7KVT6XX62GOTWDIFWG6UTC","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"16fbb343c0d6fb9acbe6a6fabf12d5f8f7e800e9148874bbf841519d025326e6","abstract_canon_sha256":"4d6ae1375798cbcf264b7e77643becf69693e34f69d4f7f4514ac4756ee8c225"},"schema_version":"1.0"},"canonical_sha256":"b64c7faab3f5efed19d3b0d05b1bd49895ad2ec21b6a277eb4952620519b3538","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:38.050523Z","signature_b64":"5usNE46VRNwZakZZ9tDUoYqEzotwNZMoHxJ913DvdS1AsauzUpbYZFIHRjZUTqQZAGPZkGS+tEFrNUSZX/cgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64c7faab3f5efed19d3b0d05b1bd49895ad2ec21b6a277eb4952620519b3538","last_reissued_at":"2026-07-05T11:15:38.049997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:38.049997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12784","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":"2026-07-05T11:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8IENbRFAAnITZl+Y6bbilvsi/de9omp8dQU6hPnMScTme4AsAu71U+XRF+Ye4U/CKz1Ck/MQEqgQu/fi4SPXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:04:20.571673Z"},"content_sha256":"ab555b289a7d26fdddc1c2ba7374773a94483ae68caab8cf6d9fc5079d38c950","schema_version":"1.0","event_id":"sha256:ab555b289a7d26fdddc1c2ba7374773a94483ae68caab8cf6d9fc5079d38c950"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WZGH7KVT6XX62GOTWDIFWG6UTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bitong Luo, Gaonan Chen, Hang Gao, Haotian Wang, Mengting Hu, Qiongyu Li, Xunzhi Wang, Zhixin Han, Zhiyu Li, Zhuowei Zhang","submitted_at":"2024-06-18T16:50:38Z","abstract_excerpt":"Despite recent progress in systematic evaluation frameworks, benchmarking the uncertainty of large language models (LLMs) remains a highly challenging task. Existing methods for benchmarking the uncertainty of LLMs face three key challenges: the need for internal model access, additional training, or high computational costs. This is particularly unfavorable for closed-source models. To this end, we introduce UBench, a new benchmark for evaluating the uncertainty of LLMs. Unlike other benchmarks, UBench is based on confidence intervals. It encompasses 11,978 multiple-choice questions spanning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12784","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/2406.12784/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":"2026-07-05T11:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ba5z/mZqWTKUPIjpN9mpGMTV/eyFld5xb+nGKDrE5fBtD28arngXwsSjloQzOIAfYcwQaRzIMIljbneCW0RBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:04:20.572313Z"},"content_sha256":"3e2d72204dfb7fd3311a6b5d4e35e45c493bd8668c9699a0fb71d5dd18449fe0","schema_version":"1.0","event_id":"sha256:3e2d72204dfb7fd3311a6b5d4e35e45c493bd8668c9699a0fb71d5dd18449fe0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZGH7KVT6XX62GOTWDIFWG6UTC/bundle.json","state_url":"https://pith.science/pith/WZGH7KVT6XX62GOTWDIFWG6UTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZGH7KVT6XX62GOTWDIFWG6UTC/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":"2026-08-11T12:04:20Z","links":{"resolver":"https://pith.science/pith/WZGH7KVT6XX62GOTWDIFWG6UTC","bundle":"https://pith.science/pith/WZGH7KVT6XX62GOTWDIFWG6UTC/bundle.json","state":"https://pith.science/pith/WZGH7KVT6XX62GOTWDIFWG6UTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZGH7KVT6XX62GOTWDIFWG6UTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WZGH7KVT6XX62GOTWDIFWG6UTC","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":"4d6ae1375798cbcf264b7e77643becf69693e34f69d4f7f4514ac4756ee8c225","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:50:38Z","title_canon_sha256":"16fbb343c0d6fb9acbe6a6fabf12d5f8f7e800e9148874bbf841519d025326e6"},"schema_version":"1.0","source":{"id":"2406.12784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12784v2","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"WZGH7KVT6XX6","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"WZGH7KVT6XX62GOT","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"WZGH7KVT","created_at":"2026-07-05T11:15:38Z"}],"graph_snapshots":[{"event_id":"sha256:3e2d72204dfb7fd3311a6b5d4e35e45c493bd8668c9699a0fb71d5dd18449fe0","target":"graph","created_at":"2026-07-05T11:15:38Z","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/2406.12784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent progress in systematic evaluation frameworks, benchmarking the uncertainty of large language models (LLMs) remains a highly challenging task. Existing methods for benchmarking the uncertainty of LLMs face three key challenges: the need for internal model access, additional training, or high computational costs. This is particularly unfavorable for closed-source models. To this end, we introduce UBench, a new benchmark for evaluating the uncertainty of LLMs. Unlike other benchmarks, UBench is based on confidence intervals. It encompasses 11,978 multiple-choice questions spanning ","authors_text":"Bitong Luo, Gaonan Chen, Hang Gao, Haotian Wang, Mengting Hu, Qiongyu Li, Xunzhi Wang, Zhixin Han, Zhiyu Li, Zhuowei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:50:38Z","title":"UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12784","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:ab555b289a7d26fdddc1c2ba7374773a94483ae68caab8cf6d9fc5079d38c950","target":"record","created_at":"2026-07-05T11:15:38Z","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":"4d6ae1375798cbcf264b7e77643becf69693e34f69d4f7f4514ac4756ee8c225","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:50:38Z","title_canon_sha256":"16fbb343c0d6fb9acbe6a6fabf12d5f8f7e800e9148874bbf841519d025326e6"},"schema_version":"1.0","source":{"id":"2406.12784","kind":"arxiv","version":2}},"canonical_sha256":"b64c7faab3f5efed19d3b0d05b1bd49895ad2ec21b6a277eb4952620519b3538","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b64c7faab3f5efed19d3b0d05b1bd49895ad2ec21b6a277eb4952620519b3538","first_computed_at":"2026-07-05T11:15:38.049997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:38.049997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5usNE46VRNwZakZZ9tDUoYqEzotwNZMoHxJ913DvdS1AsauzUpbYZFIHRjZUTqQZAGPZkGS+tEFrNUSZX/cgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:38.050523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab555b289a7d26fdddc1c2ba7374773a94483ae68caab8cf6d9fc5079d38c950","sha256:3e2d72204dfb7fd3311a6b5d4e35e45c493bd8668c9699a0fb71d5dd18449fe0"],"state_sha256":"dfb4964ba1dc53ce4de8d642ecff01266fb6e6afbb39b5a5f7e9fecc978ba5ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oh90j4rzwEEcOVqBkLCJ9d4vG6FsKP2MUnMyqHgv25Hv55lbmaXhr/TsxgW8LxiRuCWBZFtfFs1tmGPPMkQnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:04:20.578401Z","bundle_sha256":"68a2c95e18d62131f12d2f3eadcd877209a0a7d7366bab6de2ee024caf98011f"}}