{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4YVMUQOJ2TUA6NTZVZNRZGSDF4","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":"9e7642bad223f7aab231a64a023ee0def6474ab56f4ff22ca89f49af43d843b3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T10:11:37Z","title_canon_sha256":"1daeb8d720dd5cf9de5276dbd83ee7148d01c5f098773b3078e25a1b0e0d0182"},"schema_version":"1.0","source":{"id":"2406.13415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13415","created_at":"2026-07-05T09:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13415v1","created_at":"2026-07-05T09:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13415","created_at":"2026-07-05T09:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"4YVMUQOJ2TUA","created_at":"2026-07-05T09:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"4YVMUQOJ2TUA6NTZ","created_at":"2026-07-05T09:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"4YVMUQOJ","created_at":"2026-07-05T09:40:58Z"}],"graph_snapshots":[{"event_id":"sha256:8508e807ea48f43f566a4f5781fb01c71e28aa58381e3449c4288d62b5fc9093","target":"graph","created_at":"2026-07-05T09:40:58Z","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/2406.13415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a systematic comparison, it is not clear how the different methods compare to one another. To fill this gap, we present a survey and empirical comparison of estimators of factual confidence. We define an experimental framework allowing for fair comparison, covering both fact-verification and question answering. Our experiments across a series of LLMs indicate that ","authors_text":"Laura Aina, Llu\\'is M\\`arquez, Mat\\'eo Mahaut, Momchil Hardalov, Paula Czarnowska, Thomas M\\\"uller","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T10:11:37Z","title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13415","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:d57cc48a261e521dc8ae0f0201f6605f3218c6c8d416257dccf8fba3a1563d5c","target":"record","created_at":"2026-07-05T09:40:58Z","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":"9e7642bad223f7aab231a64a023ee0def6474ab56f4ff22ca89f49af43d843b3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T10:11:37Z","title_canon_sha256":"1daeb8d720dd5cf9de5276dbd83ee7148d01c5f098773b3078e25a1b0e0d0182"},"schema_version":"1.0","source":{"id":"2406.13415","kind":"arxiv","version":1}},"canonical_sha256":"e62aca41c9d4e80f3679ae5b1c9a432f37860202d455c80a5f428d4038ec94a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e62aca41c9d4e80f3679ae5b1c9a432f37860202d455c80a5f428d4038ec94a3","first_computed_at":"2026-07-05T09:40:58.647638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:58.647638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aQNXDeEwUiiCW4dPMKHtix7cyhPeI8Esksmx0cOhWbgZp9t2xpnQqYuJt17A5USPBWrKTF+ponEjuZsZH6+oCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:58.648096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d57cc48a261e521dc8ae0f0201f6605f3218c6c8d416257dccf8fba3a1563d5c","sha256:8508e807ea48f43f566a4f5781fb01c71e28aa58381e3449c4288d62b5fc9093"],"state_sha256":"143a5b27c296a52263eafb988a4fbf739f130a86049e0eee2e09dc9d2e0fc91e"}