{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04703", "kind": "paper", "url": "https://arxiv.org/abs/2608.04703"}], "authors": ["Shahd Gaben", "Heba Sbahi", "Samer Rashwani", "Abdessalam Bouchekif", "Mutaz Al-Khatib", "Emad Mohamed", "Somaya Eltanbouly", "Mohammed Ghaly"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04703", "source_url": "https://arxiv.org/abs/2608.04703"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Multi-task dataset of 3,465 QA items from 35 Islamic scholarly works, spanning 12 centuries and seven fields, with three difficulty levels and three task formats."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04703", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04703", "title": "IslamicTurathBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hamad bin Khalifa University", "Nazarbayev University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.04703", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.04703", "source_url": "https://openalex.org/W7197010576"}, "key": "claire-radar:2608.04703", "modality": null, "name": "IslamicTurathBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_islamicturathbench_0fa2de43", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "534b4ddd3fa8b777135eda28f4730bd0aacb80f79e6fc2146b4e9e280f0e5c3b", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-08T08:57:27.463024Z", "source_url": "https://arxiv.org/abs/2608.04703"}, "publisher": null, "released": "2026-08-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04703", "source_url": "https://arxiv.org/abs/2608.04703"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04703", "source": "claire_radar", "source_benchmark_id": "2608.04703", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.04703", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Niche religious domain benchmarking will attract limited broad attention but may see steady interest in specialized communities.", "score": 18}, "capabilities": [], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:57:27.463024Z", "inputHash": "49d37491692879fad58979f2fa636605652471bdd2cae5ff9be4ccab56f4a8c3", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath)", "canonicalNameSource": "paper_title", "decisionReason": "Paper presents a named dataset with public data and code, fixed questions, and clear evaluation axes; suitable for public reuse.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-08T08:57:27.463024Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Multi-task dataset of 3,465 QA items from 35 Islamic scholarly works, spanning 12 centuries and seven fields, with three difficulty levels and three task formats.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence"], "snippet": "We introduce IslamicTurathBench (ISTB), a multi-task, multi-discipline dataset for evaluating LLMs on classical Islamic scholarship."}, "familyId": "bmf_a931a8963fd7", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_islamicturathbench_0fa2de43", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.04703", "pdf": "https://arxiv.org/pdf/2608.04703", "project": null, "report": "https://arxiv.org/abs/2608.04703"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used for question answering, education, and research, including in religious and cultural domains where answers depend on specialised source traditions.", "name": "IslamicTurathBench", "oneLine": "Multi-task dataset of 3,465 QA items from 35 Islamic scholarly works, spanning 12 centuries and seven fields, with three difficulty levels and three task formats.", "paperTitle": "IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath)", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04703", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.65, "relation": "introduces", "releasedAt": "2026-08-05", "source": {"authors": ["Shahd Gaben", "Heba Sbahi", "Samer Rashwani", "Abdessalam Bouchekif", "Mutaz Al-Khatib", "Emad Mohamed", "Somaya Eltanbouly", "and Mohammed Ghaly"], "categories": ["cs.CL"], "id": "2608.04703", "title": "IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath)", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04703"}, "sourceUpdatedAt": "2026-08-05T11:12:48Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Provides expert-reviewed resources for evaluating LLMs in a culturally important, historically deep domain with reproducible scoring."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
