{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XO6JDECGRSMDAKQ234SBNAF4I6","short_pith_number":"pith:XO6JDECG","schema_version":"1.0","canonical_sha256":"bbbc9190468c98302a1adf241680bc47856001dd42e8bd935ce75735d81c9a36","source":{"kind":"arxiv","id":"2607.20219","version":1},"attestation_state":"computed","paper":{"title":"HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdenour Hadid, Abdessalam Bouchekif, Emad Mohamed, Heba Sbahi, Hichem Telli, Mohammed-En-Nadhir Zighem, Mohammed Ghaly, Mutaz Al-Khatib, Salah Eddine Bekhouche, Samer Rashwani, Shahd Gaben, Somaya Eltanbouly","submitted_at":"2026-07-22T14:37:25Z","abstract_excerpt":"Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks often provide response-level labels, with limited support for identifying the exact erroneous content, explaining why it is incorrect, or selecting the correct factual answer. We introduce \\textsc{HalluTruthQA}, a fine-grained benchmark for hallucination evaluation in Arabic question answering. The benchmark contains 2,400 expert-curated examples across four knowledge-intensive domains: Islamic knowledge, history, scien"},"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":"2607.20219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T14:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"93f42da4f58bf2e1b05cba00fab63ef9aad0ae794386fa826a503d1dee8f9791","abstract_canon_sha256":"9a2c5b7643e4c3d41a3bdcb80dfecd20f8d7818051df0f2a417ed55a6351fe86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:25:08.330207Z","signature_b64":"RUj+PBGCGpxtu8kw68SFXvx1dM67529qOZcFIh17o3xkqlthMKWkkGedOl8GUAef81VeerqWMDKZtJvtjLSfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbbc9190468c98302a1adf241680bc47856001dd42e8bd935ce75735d81c9a36","last_reissued_at":"2026-07-23T01:25:08.329352Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:25:08.329352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdenour Hadid, Abdessalam Bouchekif, Emad Mohamed, Heba Sbahi, Hichem Telli, Mohammed-En-Nadhir Zighem, Mohammed Ghaly, Mutaz Al-Khatib, Salah Eddine Bekhouche, Samer Rashwani, Shahd Gaben, Somaya Eltanbouly","submitted_at":"2026-07-22T14:37:25Z","abstract_excerpt":"Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks often provide response-level labels, with limited support for identifying the exact erroneous content, explaining why it is incorrect, or selecting the correct factual answer. We introduce \\textsc{HalluTruthQA}, a fine-grained benchmark for hallucination evaluation in Arabic question answering. The benchmark contains 2,400 expert-curated examples across four knowledge-intensive domains: Islamic knowledge, history, scien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20219","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/2607.20219/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":"2607.20219","created_at":"2026-07-23T01:25:08.329797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20219v1","created_at":"2026-07-23T01:25:08.329797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20219","created_at":"2026-07-23T01:25:08.329797+00:00"},{"alias_kind":"pith_short_12","alias_value":"XO6JDECGRSMD","created_at":"2026-07-23T01:25:08.329797+00:00"},{"alias_kind":"pith_short_16","alias_value":"XO6JDECGRSMDAKQ2","created_at":"2026-07-23T01:25:08.329797+00:00"},{"alias_kind":"pith_short_8","alias_value":"XO6JDECG","created_at":"2026-07-23T01:25:08.329797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03720","citing_title":"Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6","json":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6.json","graph_json":"https://pith.science/api/pith-number/XO6JDECGRSMDAKQ234SBNAF4I6/graph.json","events_json":"https://pith.science/api/pith-number/XO6JDECGRSMDAKQ234SBNAF4I6/events.json","paper":"https://pith.science/paper/XO6JDECG"},"agent_actions":{"view_html":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6","download_json":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6.json","view_paper":"https://pith.science/paper/XO6JDECG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20219&json=true","fetch_graph":"https://pith.science/api/pith-number/XO6JDECGRSMDAKQ234SBNAF4I6/graph.json","fetch_events":"https://pith.science/api/pith-number/XO6JDECGRSMDAKQ234SBNAF4I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6/action/storage_attestation","attest_author":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6/action/author_attestation","sign_citation":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6/action/citation_signature","submit_replication":"https://pith.science/pith/XO6JDECGRSMDAKQ234SBNAF4I6/action/replication_record"}},"created_at":"2026-07-23T01:25:08.329797+00:00","updated_at":"2026-07-23T01:25:08.329797+00:00"}