{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VO7246OALRVLBJPJFZI4WJXAB","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":"18501a9e36e3a1985133a7b9b2a496cc5bb17ce0485ed413bd6806613b7889bd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-24T09:48:48Z","title_canon_sha256":"8c970da836cd275b189d29d21ea0857995a82299e87c47be2b1657da48c950fb"},"schema_version":"1.0","source":{"id":"2407.17125","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17125","created_at":"2026-07-05T09:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17125v3","created_at":"2026-07-05T09:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17125","created_at":"2026-07-05T09:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"4VO7246OALRV","created_at":"2026-07-05T09:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"4VO7246OALRVLBJP","created_at":"2026-07-05T09:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"4VO7246O","created_at":"2026-07-05T09:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:71993917507e5109c35b83123522daa14b7d12819636729613a46783728358bd","target":"graph","created_at":"2026-07-05T09:15:58Z","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/2407.17125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the major aspects contributing to the striking performance of large language models (LLMs) is the vast amount of factual knowledge accumulated during pre-training. Yet, many LLMs suffer from self-inconsistency, which raises doubts about their trustworthiness and reliability. This paper focuses on entity type ambiguity, analyzing the proficiency and consistency of state-of-the-art LLMs in applying factual knowledge when prompted with ambiguous entities. To do so, we propose an evaluation protocol that disentangles knowing from applying knowledge, and test state-of-the-art LLMs on 49 ambi","authors_text":"Anastasiia Sedova, Barbara Plank, Benjamin Roth, Diego Frassinelli, Robert Litschko","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-24T09:48:48Z","title":"To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17125","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":"sha256:16852c861d8f8d3fba036a668db07be8b2bf86a8a10378e3a50a52af6e9c259b","target":"record","created_at":"2026-07-05T09:15:58Z","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":"18501a9e36e3a1985133a7b9b2a496cc5bb17ce0485ed413bd6806613b7889bd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-24T09:48:48Z","title_canon_sha256":"8c970da836cd275b189d29d21ea0857995a82299e87c47be2b1657da48c950fb"},"schema_version":"1.0","source":{"id":"2407.17125","kind":"arxiv","version":3}},"canonical_sha256":"e55dfd73ce02e355852f49728e5937005c0c28b0aa4dbbd53019b292f93d6935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e55dfd73ce02e355852f49728e5937005c0c28b0aa4dbbd53019b292f93d6935","first_computed_at":"2026-07-05T09:15:58.903127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:58.903127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jrOg94Y7o+2Ma+Nufs95vPau8/e6aoOS/jZVcwaxlV4HMy/4ieOQZ97uZeu4Kz+ZJcM7eW2TNeiEvFOBOiVAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:58.903567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17125","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16852c861d8f8d3fba036a668db07be8b2bf86a8a10378e3a50a52af6e9c259b","sha256:71993917507e5109c35b83123522daa14b7d12819636729613a46783728358bd"],"state_sha256":"6883e2e6b348afeaeed7ce5b2a60c8c72ca57e4265878d44150e436035588dbb"}