{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05531", "kind": "paper", "url": "https://arxiv.org/abs/2606.05531"}, {"id": "gh:qcri/almieyar-oryx-bloombench", "kind": "repo", "url": "https://github.com/qcri/Almieyar-Oryx-BloomBench"}], "authors": ["Mohammad Mahdi Abootorabi", "Omid Ghahroodi", "Anas Madkoor", "Marzia Nouri", "Doratossadat Dastgheib", "Mohamed Hefeeda", "Ehsaneddin Asgari"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05531", "source_url": "https://arxiv.org/abs/2606.05531"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Evaluates vision-language models on six cognitive levels (Remember to Create) with bilingual English-Arabic image-question-answer tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05531", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05531", "title": "Almieyar-Oryx-BloomBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hamad bin Khalifa University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05531", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05531", "source_url": "https://openalex.org/W7163674860"}, "key": "claire-radar:2606.05531", "modality": null, "name": "Almieyar-Oryx-BloomBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_almieyar-oryx-bloombench_1b7c3bae", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "817f81986790af8da84f345b72c27d1924c5744f589c1786432378ba718e9576", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05531"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05531", "source_url": "https://arxiv.org/abs/2606.05531"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05531", "source": "claire_radar", "source_benchmark_id": "2606.05531", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "githubScope": "benchmark_repo", "githubStars": 7, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 8, "hfPaperUrl": "https://huggingface.co/papers/2606.05531", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b3a48c0c45ee0fd16be453dd9419f047d09009f8c47f8a2838537a72ad1eb201", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vision-language models on six cognitive levels (Remember to Create) with bilingual English-Arabic image-question-answer tasks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce BloomBench, part of the Almieyar benchmarking series, the first cognitively human-grounded, bilingual (English-Arabic) multimodal benchmark for VLMs."}, "familyId": "bmf_314bc62a1b7c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "url": "https://github.com/qcri/Almieyar-Oryx-BloomBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "url": "https://huggingface.co/papers/2606.05531"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "url": "https://huggingface.co/api/papers/2606.05531"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/qcri/Almieyar-Oryx-BloomBench.", "url": "https://arxiv.org/abs/2606.05531"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "url": "https://arxiv.org/abs/2606.05531"}], "scope": "benchmark_repo", "url": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_almieyar-oryx-bloombench_1b7c3bae", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/qcri/Almieyar-Oryx-BloomBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.05531", "paper": "https://arxiv.org/abs/2606.05531", "pdf": "https://arxiv.org/pdf/2606.05531", "project": null, "report": "https://arxiv.org/abs/2606.05531"}, "metrics": [], "motivation": "Despite the rapid progress of Vision-Language Models (VLMs), the field lacks benchmarks that rigorously diagnose their true reasoning abilities and chart meaningful progress toward human-like multimodal intelligence.", "name": "Almieyar-Oryx-BloomBench", "oneLine": "Evaluates vision-language models on six cognitive levels (Remember to Create) with bilingual English-Arabic image-question-answer tasks.", "paperTitle": "Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to ACL 2026 Findings", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.05531", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ACL 2026 Findings", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "QCRI", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/qcri/Almieyar-Oryx-BloomBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-04", "source": {"authors": ["Mohammad Mahdi Abootorabi", "Omid Ghahroodi", "Anas Madkoor", "Marzia Nouri", "Doratossadat Dastgheib", "Mohamed Hefeeda", "Ehsaneddin Asgari"], "categories": ["cs.CV", "cs.AI", "cs.CL", "cs.LG"], "id": "2606.05531", "title": "Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05531"}, "sourceUpdatedAt": "2026-06-04T00:21:22Z", "topics": ["Multimodal"], "venueAttempts": [{"decisionRaw": "Accepted to ACL 2026 Findings", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to ACL 2026 Findings", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.05531"}], "reviewStatus": "accepted", "venueName": "ACL 2026 Findings"}], "whyItMatters": "Provides a cognitively grounded benchmark to diagnose reasoning strengths/weaknesses across levels and languages, addressing gaps in existing piecemeal evaluations."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
