{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WIN6CH4Q7QGPPRPL2T6R7XA5JF","short_pith_number":"pith:WIN6CH4Q","schema_version":"1.0","canonical_sha256":"b21be11f90fc0cf7c5ebd4fd1fdc1d496cf8fc2425934d8ba32d418017fd9d3a","source":{"kind":"arxiv","id":"2601.07528","version":2},"attestation_state":"computed","paper":{"title":"From RAG to Agentic RAG for Faithful Islamic Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fadi Zaraket, Firoj Alam, Gagan Bhatia, George Mikros, Hamdy Mubarak, Kareem Darwish, Logan Cochrane, Mahmoud Alhirthani, Mustafa Jarrar, Mutaz Al-Khatib, Rashid Yahiaoui","submitted_at":"2026-01-12T13:28:28Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used for Islamic question answering, where ungrounded responses may carry serious religious consequences. Yet standard MCQ/MRC-style evaluations (MCQ: Multiple choice questions, MRC: Machine Reading Comprehension) do not capture key real-world failure modes, notably free-form hallucinations and the ability to abstain when evidence is insufficient. To address this gap, we introduce IslamicFaithQA, a 3,810-item bilingual (Arabic/English) generative benchmark with atomic single-gold answers, which enables direct measurement of hallucination and absten"},"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":"2601.07528","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-12T13:28:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5e770b16ccf57e7634c457404a86ead9182398e6e7e215bfb838a8e9fe03fe9b","abstract_canon_sha256":"1398e714860456635d9705ddd77c2fb73c511e6675c1692abc9a6f35007a30b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:00.187213Z","signature_b64":"Z953fSOLuhyQ5LJw+36zeDt3TaXnYTwJFL8683bWa0bhES1Gqb5yrAm+offhqLHR/7nb9OhWKoDHTFcgCpoBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b21be11f90fc0cf7c5ebd4fd1fdc1d496cf8fc2425934d8ba32d418017fd9d3a","last_reissued_at":"2026-06-23T01:12:00.186654Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:00.186654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From RAG to Agentic RAG for Faithful Islamic Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fadi Zaraket, Firoj Alam, Gagan Bhatia, George Mikros, Hamdy Mubarak, Kareem Darwish, Logan Cochrane, Mahmoud Alhirthani, Mustafa Jarrar, Mutaz Al-Khatib, Rashid Yahiaoui","submitted_at":"2026-01-12T13:28:28Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used for Islamic question answering, where ungrounded responses may carry serious religious consequences. Yet standard MCQ/MRC-style evaluations (MCQ: Multiple choice questions, MRC: Machine Reading Comprehension) do not capture key real-world failure modes, notably free-form hallucinations and the ability to abstain when evidence is insufficient. To address this gap, we introduce IslamicFaithQA, a 3,810-item bilingual (Arabic/English) generative benchmark with atomic single-gold answers, which enables direct measurement of hallucination and absten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07528","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/2601.07528/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":"2601.07528","created_at":"2026-06-23T01:12:00.186732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.07528v2","created_at":"2026-06-23T01:12:00.186732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07528","created_at":"2026-06-23T01:12:00.186732+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIN6CH4Q7QGP","created_at":"2026-06-23T01:12:00.186732+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIN6CH4Q7QGPPRPL","created_at":"2026-06-23T01:12:00.186732+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIN6CH4Q","created_at":"2026-06-23T01:12:00.186732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF","json":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF.json","graph_json":"https://pith.science/api/pith-number/WIN6CH4Q7QGPPRPL2T6R7XA5JF/graph.json","events_json":"https://pith.science/api/pith-number/WIN6CH4Q7QGPPRPL2T6R7XA5JF/events.json","paper":"https://pith.science/paper/WIN6CH4Q"},"agent_actions":{"view_html":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF","download_json":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF.json","view_paper":"https://pith.science/paper/WIN6CH4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.07528&json=true","fetch_graph":"https://pith.science/api/pith-number/WIN6CH4Q7QGPPRPL2T6R7XA5JF/graph.json","fetch_events":"https://pith.science/api/pith-number/WIN6CH4Q7QGPPRPL2T6R7XA5JF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF/action/storage_attestation","attest_author":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF/action/author_attestation","sign_citation":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF/action/citation_signature","submit_replication":"https://pith.science/pith/WIN6CH4Q7QGPPRPL2T6R7XA5JF/action/replication_record"}},"created_at":"2026-06-23T01:12:00.186732+00:00","updated_at":"2026-06-23T01:12:00.186732+00:00"}