{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HJZT4AXNF3P3VUBKP2HMOVMWO3","short_pith_number":"pith:HJZT4AXN","schema_version":"1.0","canonical_sha256":"3a733e02ed2edfbad02a7e8ec7559676ecf3691b393550606e5b8602eacb3256","source":{"kind":"arxiv","id":"2503.16541","version":2},"attestation_state":"computed","paper":{"title":"Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanzhi Zhang, Heng Fan, Sumera Anjum, Weijian Zheng, Yan Huang, Yunhe Feng","submitted_at":"2025-03-19T01:46:09Z","abstract_excerpt":"Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for hallucination detection focus primarily on English and a few widely spoken languages, lacking the breadth to assess inconsistencies in model performance across diverse linguistic contexts. To address this gap, we introduce Poly-FEVER, a large-scale multilingual fact verification benchmark specifically designed for evaluating hallucination detection in LLMs. Poly-FEVER comprises 77,973 labeled factual claims spanning"},"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":"2503.16541","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T01:46:09Z","cross_cats_sorted":[],"title_canon_sha256":"0f61de841511d42e351de221e2c0e5e0a55681be3551be6da25d60816e20c261","abstract_canon_sha256":"904def3ab032e875ff2d7c55c39c5b3d9cca9e06ba727b55f32d755c7c5d63b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:47.844185Z","signature_b64":"AqEURFYE7bfGwza4EjLB3lrtz8YywKfGXjYlw9/y+Xg7ctwr7+EYbJ5k+M+efOGLgNvUOOaoas5OAlFDppaOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a733e02ed2edfbad02a7e8ec7559676ecf3691b393550606e5b8602eacb3256","last_reissued_at":"2026-07-05T10:39:47.843679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:47.843679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanzhi Zhang, Heng Fan, Sumera Anjum, Weijian Zheng, Yan Huang, Yunhe Feng","submitted_at":"2025-03-19T01:46:09Z","abstract_excerpt":"Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for hallucination detection focus primarily on English and a few widely spoken languages, lacking the breadth to assess inconsistencies in model performance across diverse linguistic contexts. To address this gap, we introduce Poly-FEVER, a large-scale multilingual fact verification benchmark specifically designed for evaluating hallucination detection in LLMs. Poly-FEVER comprises 77,973 labeled factual claims spanning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16541","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/2503.16541/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":"2503.16541","created_at":"2026-07-05T10:39:47.843739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16541v2","created_at":"2026-07-05T10:39:47.843739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16541","created_at":"2026-07-05T10:39:47.843739+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJZT4AXNF3P3","created_at":"2026-07-05T10:39:47.843739+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJZT4AXNF3P3VUBK","created_at":"2026-07-05T10:39:47.843739+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJZT4AXN","created_at":"2026-07-05T10:39:47.843739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17007","citing_title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3","json":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3.json","graph_json":"https://pith.science/api/pith-number/HJZT4AXNF3P3VUBKP2HMOVMWO3/graph.json","events_json":"https://pith.science/api/pith-number/HJZT4AXNF3P3VUBKP2HMOVMWO3/events.json","paper":"https://pith.science/paper/HJZT4AXN"},"agent_actions":{"view_html":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3","download_json":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3.json","view_paper":"https://pith.science/paper/HJZT4AXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16541&json=true","fetch_graph":"https://pith.science/api/pith-number/HJZT4AXNF3P3VUBKP2HMOVMWO3/graph.json","fetch_events":"https://pith.science/api/pith-number/HJZT4AXNF3P3VUBKP2HMOVMWO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3/action/storage_attestation","attest_author":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3/action/author_attestation","sign_citation":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3/action/citation_signature","submit_replication":"https://pith.science/pith/HJZT4AXNF3P3VUBKP2HMOVMWO3/action/replication_record"}},"created_at":"2026-07-05T10:39:47.843739+00:00","updated_at":"2026-07-05T10:39:47.843739+00:00"}