{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GAPDGOPRXPIVL4344XQPSIJFKW","short_pith_number":"pith:GAPDGOPR","canonical_record":{"source":{"id":"2410.14582","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T16:32:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d2882bef67be65dd9026d61ec1734966ef5d78679c68a92ab0828ec3972cf066","abstract_canon_sha256":"e208331cb92534fdacef6667f644265852097b96fd02618ffc36cf7813bbb880"},"schema_version":"1.0"},"canonical_sha256":"301e3339f1bbd155f37ce5e0f921255595f57ca8858f07b6411111d236345bd4","source":{"kind":"arxiv","id":"2410.14582","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14582","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14582v4","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14582","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"GAPDGOPRXPIV","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"GAPDGOPRXPIVL434","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"GAPDGOPR","created_at":"2026-07-05T10:40:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GAPDGOPRXPIVL4344XQPSIJFKW","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14582","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T16:32:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d2882bef67be65dd9026d61ec1734966ef5d78679c68a92ab0828ec3972cf066","abstract_canon_sha256":"e208331cb92534fdacef6667f644265852097b96fd02618ffc36cf7813bbb880"},"schema_version":"1.0"},"canonical_sha256":"301e3339f1bbd155f37ce5e0f921255595f57ca8858f07b6411111d236345bd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:59.097648Z","signature_b64":"cPyKeS23WxFPs0iCGhIYPaGK7bF0TVBXehNMky8RxwXvQcMr+waQdtdZ6tJ09X8KkETSmuevV7D5ldjIlywMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"301e3339f1bbd155f37ce5e0f921255595f57ca8858f07b6411111d236345bd4","last_reissued_at":"2026-07-05T10:40:59.097128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:59.097128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14582","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YSbb5mBWqmfw2x0bgjMWu59sAXsGUwanq23GWNc935psSPJCNgkgMuUALPlFNunjs/+72NP7x9UADVokMFUSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:17:10.845151Z"},"content_sha256":"d80d92795be2ad555ddacaa7f0d022e82ab4dde940fb9018bc05df3c2a9dc5e0","schema_version":"1.0","event_id":"sha256:d80d92795be2ad555ddacaa7f0d022e82ab4dde940fb9018bc05df3c2a9dc5e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GAPDGOPRXPIVL4344XQPSIJFKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do LLMs estimate uncertainty well in instruction-following?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Christina Heinze-Deml, Jaya Narain, Juyeon Heo, Miao Xiong","submitted_at":"2024-10-18T16:32:10Z","abstract_excerpt":"Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following capabilities, raising concerns about their reliability in high-stakes applications. Accurately estimating LLMs' uncertainty in adhering to instructions is critical to mitigating deployment risks. We present, to our knowledge, the first systematic evaluation of the uncertainty estimation abilities of LLMs in the context of instruction-following. Our study identifie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14582","kind":"arxiv","version":4},"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/2410.14582/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":"2026-07-05T10:40:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScZU8aGIxxkhczj0GHp8+Ji4lBzvT1QQfg6x56VozjrWMkR7/PJ1PCMjE9xu99yS1wszcYNy87NhcarbV2boAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:17:10.845811Z"},"content_sha256":"68f0ea709a8bdc6e13fe92ecbfa3466f15ed5782d21123e013c9ac73af2a04ad","schema_version":"1.0","event_id":"sha256:68f0ea709a8bdc6e13fe92ecbfa3466f15ed5782d21123e013c9ac73af2a04ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAPDGOPRXPIVL4344XQPSIJFKW/bundle.json","state_url":"https://pith.science/pith/GAPDGOPRXPIVL4344XQPSIJFKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAPDGOPRXPIVL4344XQPSIJFKW/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":"2026-08-06T07:17:10Z","links":{"resolver":"https://pith.science/pith/GAPDGOPRXPIVL4344XQPSIJFKW","bundle":"https://pith.science/pith/GAPDGOPRXPIVL4344XQPSIJFKW/bundle.json","state":"https://pith.science/pith/GAPDGOPRXPIVL4344XQPSIJFKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAPDGOPRXPIVL4344XQPSIJFKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GAPDGOPRXPIVL4344XQPSIJFKW","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":"e208331cb92534fdacef6667f644265852097b96fd02618ffc36cf7813bbb880","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T16:32:10Z","title_canon_sha256":"d2882bef67be65dd9026d61ec1734966ef5d78679c68a92ab0828ec3972cf066"},"schema_version":"1.0","source":{"id":"2410.14582","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14582","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14582v4","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14582","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"GAPDGOPRXPIV","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"GAPDGOPRXPIVL434","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"GAPDGOPR","created_at":"2026-07-05T10:40:59Z"}],"graph_snapshots":[{"event_id":"sha256:68f0ea709a8bdc6e13fe92ecbfa3466f15ed5782d21123e013c9ac73af2a04ad","target":"graph","created_at":"2026-07-05T10:40:59Z","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/2410.14582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following capabilities, raising concerns about their reliability in high-stakes applications. Accurately estimating LLMs' uncertainty in adhering to instructions is critical to mitigating deployment risks. We present, to our knowledge, the first systematic evaluation of the uncertainty estimation abilities of LLMs in the context of instruction-following. Our study identifie","authors_text":"Christina Heinze-Deml, Jaya Narain, Juyeon Heo, Miao Xiong","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T16:32:10Z","title":"Do LLMs estimate uncertainty well in instruction-following?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14582","kind":"arxiv","version":4},"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:d80d92795be2ad555ddacaa7f0d022e82ab4dde940fb9018bc05df3c2a9dc5e0","target":"record","created_at":"2026-07-05T10:40:59Z","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":"e208331cb92534fdacef6667f644265852097b96fd02618ffc36cf7813bbb880","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T16:32:10Z","title_canon_sha256":"d2882bef67be65dd9026d61ec1734966ef5d78679c68a92ab0828ec3972cf066"},"schema_version":"1.0","source":{"id":"2410.14582","kind":"arxiv","version":4}},"canonical_sha256":"301e3339f1bbd155f37ce5e0f921255595f57ca8858f07b6411111d236345bd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"301e3339f1bbd155f37ce5e0f921255595f57ca8858f07b6411111d236345bd4","first_computed_at":"2026-07-05T10:40:59.097128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:59.097128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cPyKeS23WxFPs0iCGhIYPaGK7bF0TVBXehNMky8RxwXvQcMr+waQdtdZ6tJ09X8KkETSmuevV7D5ldjIlywMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:59.097648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14582","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d80d92795be2ad555ddacaa7f0d022e82ab4dde940fb9018bc05df3c2a9dc5e0","sha256:68f0ea709a8bdc6e13fe92ecbfa3466f15ed5782d21123e013c9ac73af2a04ad"],"state_sha256":"c16958094e1b629d8a32053958aca6a68b61c06d3888e063d52b068a127bf8ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsuXsSI3i0J4VCPIV/ksPyGkve8nguiEC3Lvx/9AgLIgI71Laws78DKSu8VtFx1+VHFgpNVxc3s++sdjUvFZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:17:10.851575Z","bundle_sha256":"77338ebbdf8afdacee2849b8638d6b3de171c9d0f3b12efb3d4d7ed1724ad8f6"}}