{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWPPO5TYZFU4WK2LCOM2UJYUBI","short_pith_number":"pith:NWPPO5TY","schema_version":"1.0","canonical_sha256":"6d9ef77678c969cb2b4b1399aa27140a293ecfdb764e85dc409ba30541809d64","source":{"kind":"arxiv","id":"2402.12545","version":2},"attestation_state":"computed","paper":{"title":"TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danna Zheng, Danyang Liu, Jeff Z. Pan, Mirella Lapata","submitted_at":"2024-02-19T21:12:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.12545","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:12:14Z","cross_cats_sorted":[],"title_canon_sha256":"b52d139339ca25081f1d97645f67949d4945ce3138bde84294598d0fd9237745","abstract_canon_sha256":"1726be6dc8e15628de56f4cbe6a98462a7d4c4728f90dc9ed1cf99a241f987da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:08.637692Z","signature_b64":"fO8nbWnd8lm5L7I+ODs5FSbthhM52dDdDXKHPYjWpqFmuNtkTJBk8/soP7XbKPFIBLzLQzvbwe1Bk/YgIDTQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d9ef77678c969cb2b4b1399aa27140a293ecfdb764e85dc409ba30541809d64","last_reissued_at":"2026-07-05T08:16:08.637218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:08.637218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danna Zheng, Danyang Liu, Jeff Z. Pan, Mirella Lapata","submitted_at":"2024-02-19T21:12:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12545","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.12545/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.12545","created_at":"2026-07-05T08:16:08.637289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12545v2","created_at":"2026-07-05T08:16:08.637289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12545","created_at":"2026-07-05T08:16:08.637289+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWPPO5TYZFU4","created_at":"2026-07-05T08:16:08.637289+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWPPO5TYZFU4WK2L","created_at":"2026-07-05T08:16:08.637289+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWPPO5TY","created_at":"2026-07-05T08:16:08.637289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.02546","citing_title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI","json":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI.json","graph_json":"https://pith.science/api/pith-number/NWPPO5TYZFU4WK2LCOM2UJYUBI/graph.json","events_json":"https://pith.science/api/pith-number/NWPPO5TYZFU4WK2LCOM2UJYUBI/events.json","paper":"https://pith.science/paper/NWPPO5TY"},"agent_actions":{"view_html":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI","download_json":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI.json","view_paper":"https://pith.science/paper/NWPPO5TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12545&json=true","fetch_graph":"https://pith.science/api/pith-number/NWPPO5TYZFU4WK2LCOM2UJYUBI/graph.json","fetch_events":"https://pith.science/api/pith-number/NWPPO5TYZFU4WK2LCOM2UJYUBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI/action/storage_attestation","attest_author":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI/action/author_attestation","sign_citation":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI/action/citation_signature","submit_replication":"https://pith.science/pith/NWPPO5TYZFU4WK2LCOM2UJYUBI/action/replication_record"}},"created_at":"2026-07-05T08:16:08.637289+00:00","updated_at":"2026-07-05T08:16:08.637289+00:00"}