{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L656LQF5LQIMRTDDRL6WSYXEXB","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":"e019c418e5580be0d72c803e8cffb7563a176819bb7bffc1f221c61e690a52f7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-14T19:09:22Z","title_canon_sha256":"7e1149bb1356531b6c2ede7337c049ff77a23a606644a286597042513a2e3262"},"schema_version":"1.0","source":{"id":"2312.09300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09300","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09300v1","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09300","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"L656LQF5LQIM","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"L656LQF5LQIMRTDD","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"L656LQF5","created_at":"2026-07-05T07:24:22Z"}],"graph_snapshots":[{"event_id":"sha256:dec7938cd72ede2be31190805d4f5fe9c7779d50e7b89e2e9589be72c7ac0996","target":"graph","created_at":"2026-07-05T07:24:22Z","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/2312.09300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely employed, recent research has demonstrated the limitations of using sequence-level probability estimates given by LLMs as reliable indicators of generation quality. Conversely, LLMs have demonstrated strong calibration at the token level, particularly when it comes to choosing correct answers in multiple-choice questions or evaluating true/false statements. I","authors_text":"Balaji Lakshminarayanan, Jie Ren, Peter J. Liu, Tu Vu, Yao Zhao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-14T19:09:22Z","title":"Self-Evaluation Improves Selective Generation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09300","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":"sha256:2379cc07e38e83741924b2fbcfd8cab8225a74fbfaf73109dd9cdeee55ade228","target":"record","created_at":"2026-07-05T07:24:22Z","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":"e019c418e5580be0d72c803e8cffb7563a176819bb7bffc1f221c61e690a52f7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-14T19:09:22Z","title_canon_sha256":"7e1149bb1356531b6c2ede7337c049ff77a23a606644a286597042513a2e3262"},"schema_version":"1.0","source":{"id":"2312.09300","kind":"arxiv","version":1}},"canonical_sha256":"5fbbe5c0bd5c10c8cc638afd6962e4b87891e7b056cb10d8347421393d8826d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fbbe5c0bd5c10c8cc638afd6962e4b87891e7b056cb10d8347421393d8826d3","first_computed_at":"2026-07-05T07:24:22.977661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:22.977661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ZRE9AFJonBYd1fGQF0jFubP1HBEmL+OfYGV11AsNliQrGL8ud+jfuKjGodCY+BSCFj7QkovJguOlaZLCPqtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:22.978099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2379cc07e38e83741924b2fbcfd8cab8225a74fbfaf73109dd9cdeee55ade228","sha256:dec7938cd72ede2be31190805d4f5fe9c7779d50e7b89e2e9589be72c7ac0996"],"state_sha256":"f83ad0992c5893237863584c42205cff48089d1e9d102d2023a0b785ab9fcb34"}