{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NWPPO5TYZFU4WK2LCOM2UJYUBI","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":"1726be6dc8e15628de56f4cbe6a98462a7d4c4728f90dc9ed1cf99a241f987da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:12:14Z","title_canon_sha256":"b52d139339ca25081f1d97645f67949d4945ce3138bde84294598d0fd9237745"},"schema_version":"1.0","source":{"id":"2402.12545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12545","created_at":"2026-07-05T08:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12545v2","created_at":"2026-07-05T08:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12545","created_at":"2026-07-05T08:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"NWPPO5TYZFU4","created_at":"2026-07-05T08:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"NWPPO5TYZFU4WK2L","created_at":"2026-07-05T08:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"NWPPO5TY","created_at":"2026-07-05T08:16:08Z"}],"graph_snapshots":[{"event_id":"sha256:3607aa14996b60a5bdc77e427eac4159a0c8de9d914f26716544b26c016cc5cc","target":"graph","created_at":"2026-07-05T08:16:08Z","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/2402.12545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. However, concerns have arisen regarding the trustworthiness of LLMs outputs, particularly in closed-book question-answering tasks, where non-experts may struggle to identify inaccuracies due to the absence of contextual or ground truth information. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge. Additionally, TrustScore can seam","authors_text":"Danna Zheng, Danyang Liu, Jeff Z. Pan, Mirella Lapata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:12:14Z","title":"TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12545","kind":"arxiv","version":2},"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:a7988d792c9d36af1e91e9c0a12e089b0f2b715e9c590926172a00131ce9ff43","target":"record","created_at":"2026-07-05T08:16:08Z","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":"1726be6dc8e15628de56f4cbe6a98462a7d4c4728f90dc9ed1cf99a241f987da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:12:14Z","title_canon_sha256":"b52d139339ca25081f1d97645f67949d4945ce3138bde84294598d0fd9237745"},"schema_version":"1.0","source":{"id":"2402.12545","kind":"arxiv","version":2}},"canonical_sha256":"6d9ef77678c969cb2b4b1399aa27140a293ecfdb764e85dc409ba30541809d64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d9ef77678c969cb2b4b1399aa27140a293ecfdb764e85dc409ba30541809d64","first_computed_at":"2026-07-05T08:16:08.637218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:08.637218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fO8nbWnd8lm5L7I+ODs5FSbthhM52dDdDXKHPYjWpqFmuNtkTJBk8/soP7XbKPFIBLzLQzvbwe1Bk/YgIDTQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:08.637692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7988d792c9d36af1e91e9c0a12e089b0f2b715e9c590926172a00131ce9ff43","sha256:3607aa14996b60a5bdc77e427eac4159a0c8de9d914f26716544b26c016cc5cc"],"state_sha256":"1df16b4704ba275b31c5f059cee131487e26f9dcef02be905ab64123c2f4449d"}