{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ENNG6RBPOHVMNKEVDNPDECXCQ6","short_pith_number":"pith:ENNG6RBP","schema_version":"1.0","canonical_sha256":"235a6f442f71eac6a8951b5e320ae287af69a704d181fe41ad46a76d96636a17","source":{"kind":"arxiv","id":"2407.10793","version":1},"attestation_state":"computed","paper":{"title":"GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hannah Sansford, Hermina Petric Maretic, Juba Nait Saada, Nicholas Richardson","submitted_at":"2024-07-15T15:11:16Z","abstract_excerpt":"Methods to evaluate Large Language Model (LLM) responses and detect inconsistencies, also known as hallucinations, with respect to the provided knowledge, are becoming increasingly important for LLM applications. Current metrics fall short in their ability to provide explainable decisions, systematically check all pieces of information in the response, and are often too computationally expensive to be used in practice. We present GraphEval: a hallucination evaluation framework based on representing information in Knowledge Graph (KG) structures. Our method identifies the specific triples in th"},"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":"2407.10793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:11:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7835b237e3b6f9ed71b91f6f039b12ff056357bf8875568d3673484baec7c0cb","abstract_canon_sha256":"33ec35804fa3f631e2f3d9e616951ab6bfee513a0795a744f2764e366e989b6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:04.118175Z","signature_b64":"YEOrjkP1y39uCgzjxVguov03VRmUPPHRU80KtcrXsnCRMPA3Wni0mf3+JzX+X+Xik6MmUFn1LGHSoniGotdBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"235a6f442f71eac6a8951b5e320ae287af69a704d181fe41ad46a76d96636a17","last_reissued_at":"2026-07-05T08:44:04.117685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:04.117685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hannah Sansford, Hermina Petric Maretic, Juba Nait Saada, Nicholas Richardson","submitted_at":"2024-07-15T15:11:16Z","abstract_excerpt":"Methods to evaluate Large Language Model (LLM) responses and detect inconsistencies, also known as hallucinations, with respect to the provided knowledge, are becoming increasingly important for LLM applications. Current metrics fall short in their ability to provide explainable decisions, systematically check all pieces of information in the response, and are often too computationally expensive to be used in practice. We present GraphEval: a hallucination evaluation framework based on representing information in Knowledge Graph (KG) structures. Our method identifies the specific triples in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10793","kind":"arxiv","version":1},"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/2407.10793/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":"2407.10793","created_at":"2026-07-05T08:44:04.117746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10793v1","created_at":"2026-07-05T08:44:04.117746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10793","created_at":"2026-07-05T08:44:04.117746+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENNG6RBPOHVM","created_at":"2026-07-05T08:44:04.117746+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENNG6RBPOHVMNKEV","created_at":"2026-07-05T08:44:04.117746+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENNG6RBP","created_at":"2026-07-05T08:44:04.117746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21517","citing_title":"MedHal-Loc: Are \"Explainable-by-Architecture\" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmark","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08157","citing_title":"Cross Paraphrastic Invariance Learning for Hallucination Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00918","citing_title":"From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15951","citing_title":"Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6","json":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6.json","graph_json":"https://pith.science/api/pith-number/ENNG6RBPOHVMNKEVDNPDECXCQ6/graph.json","events_json":"https://pith.science/api/pith-number/ENNG6RBPOHVMNKEVDNPDECXCQ6/events.json","paper":"https://pith.science/paper/ENNG6RBP"},"agent_actions":{"view_html":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6","download_json":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6.json","view_paper":"https://pith.science/paper/ENNG6RBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10793&json=true","fetch_graph":"https://pith.science/api/pith-number/ENNG6RBPOHVMNKEVDNPDECXCQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ENNG6RBPOHVMNKEVDNPDECXCQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6/action/storage_attestation","attest_author":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6/action/author_attestation","sign_citation":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6/action/citation_signature","submit_replication":"https://pith.science/pith/ENNG6RBPOHVMNKEVDNPDECXCQ6/action/replication_record"}},"created_at":"2026-07-05T08:44:04.117746+00:00","updated_at":"2026-07-05T08:44:04.117746+00:00"}