{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VSR3DGPKPPQOB7I64TBSN3AXJG","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":"b4ab67460624b21c03cd2337072b1590ad2404ed82cfec16675ddce2eb6453cd","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T15:26:10Z","title_canon_sha256":"876a9a85ade0b532274a3d7208ce76dd34780b30f42723410ae2e394c9f28c3f"},"schema_version":"1.0","source":{"id":"2305.18404","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18404","created_at":"2026-07-05T06:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18404v3","created_at":"2026-07-05T06:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18404","created_at":"2026-07-05T06:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"VSR3DGPKPPQO","created_at":"2026-07-05T06:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"VSR3DGPKPPQOB7I6","created_at":"2026-07-05T06:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"VSR3DGPK","created_at":"2026-07-05T06:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:edd8db42e589ed974b66935b92df89bc7a4a009dd1c08326f0a177aa7f162e94","target":"graph","created_at":"2026-07-05T06:29:02Z","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/2305.18404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models continue to be widely developed, robust uncertainty quantification techniques will become crucial for their safe deployment in high-stakes scenarios. In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering. We find that the uncertainty estimates from conformal prediction are tightly correlated with prediction accuracy. This observation can be useful for downstream applications such as selective classification and filtering out low-quality predictio","authors_text":"Andrew Beam, Anil Palepu, Bhawesh Kumar, Charlie Lu, David Bellamy, Gauri Gupta, Ramesh Raskar","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T15:26:10Z","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18404","kind":"arxiv","version":3},"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":"sha256:5940be71fc9d33c119155192f7f52d2dcaead85059f602ba3424a47b41035b85","target":"record","created_at":"2026-07-05T06:29:02Z","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":"b4ab67460624b21c03cd2337072b1590ad2404ed82cfec16675ddce2eb6453cd","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T15:26:10Z","title_canon_sha256":"876a9a85ade0b532274a3d7208ce76dd34780b30f42723410ae2e394c9f28c3f"},"schema_version":"1.0","source":{"id":"2305.18404","kind":"arxiv","version":3}},"canonical_sha256":"aca3b199ea7be0e0fd1ee4c326ec1749ab82af505a9f327f6744f868bcff2a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aca3b199ea7be0e0fd1ee4c326ec1749ab82af505a9f327f6744f868bcff2a4d","first_computed_at":"2026-07-05T06:29:02.121000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:02.121000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3u/f5kK7eM4yjR3XJeaAyg2/uFR9Rl6w/CN6xICESClnNqWzvj6YDWHUvf3gNRjJVJs7S1BFEJeDSo//IBR9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:02.121536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18404","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5940be71fc9d33c119155192f7f52d2dcaead85059f602ba3424a47b41035b85","sha256:edd8db42e589ed974b66935b92df89bc7a4a009dd1c08326f0a177aa7f162e94"],"state_sha256":"0dd53d92a3d9d7a403b0355723bf2bccf85f97476076701df9350761651dc688"}