{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.02007", "kind": "paper", "url": "https://arxiv.org/abs/2607.02007"}], "authors": ["Gianmarco Spinaci", "Lukas Klic", "Giovanni Colavizza"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.02007", "source_url": "https://arxiv.org/abs/2607.02007"}, "categories": ["Factuality", "General AI", "Multimodal", "Reasoning"], "description": {"en": "EduArt evaluates art-historical knowledge and visual reasoning in multimodal LLMs using 871 human-authored questions in Italian and English, covering multiple formats and languages. Scoring is based on accuracy and psychometric properties."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.02007", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.02007", "title": "EduArt"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Copenhagen", "IT University of Copenhagen", "University of Bologna"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.02007", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.02007", "source_url": "https://openalex.org/W7167284612"}, "key": "claire-radar:2607.02007", "modality": null, "name": "EduArt", "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_eduart_6e0cd321", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "731eae08ce8c8105d2aeddc277bb66f4587431564c399fa5b88614f70eb15b25", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.02007"}, "publisher": null, "released": "2026-07-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.02007", "source_url": "https://arxiv.org/abs/2607.02007"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-02007", "source": "claire_radar", "source_benchmark_id": "2607.02007", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Multimodal", "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/2607.02007", "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"}, "capabilities": ["Reasoning", "Factuality"], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "dbb51aece7ec6c9f44b723106dfcb5e8c97989d5a966442965c740fbd4fb9ffc", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EduArt evaluates art-historical knowledge and visual reasoning in multimodal LLMs using 871 human-authored questions in Italian and English, covering multiple formats and languages. Scoring is based on accuracy and psychometric properties.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "This paper introduces EduArt, an educational-level benchmark for art-historical knowledge and visual reasoning in multimodal LLMs."}, "familyId": "bmf_b8da88c300f6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_eduart_6e0cd321", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.02007", "paper": "https://arxiv.org/abs/2607.02007", "pdf": "https://arxiv.org/pdf/2607.02007", "project": null, "report": "https://arxiv.org/abs/2607.02007"}, "metrics": [], "motivation": "Large language models now score near ceiling on general benchmarks, but these aggregate measures reveal little about how models behave within single disciplines.", "name": "EduArt", "oneLine": "EduArt evaluates art-historical knowledge and visual reasoning in multimodal LLMs using 871 human-authored questions in Italian and English, covering multiple formats and languages. Scoring is based on accuracy and psychometric properties.", "paperTitle": "EduArt: An educational-level benchmark for evaluating art history knowledge in large language models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.02007", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.02007"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-02", "source": {"authors": ["Gianmarco Spinaci", "Lukas Klic", "Giovanni Colavizza"], "categories": ["cs.CL", "cs.CV"], "id": "2607.02007", "title": "EduArt: An educational-level benchmark for evaluating art history knowledge in large language models", "type": "arxiv", "url": "https://arxiv.org/abs/2607.02007"}, "sourceUpdatedAt": "2026-07-02T10:43:06Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "General benchmarks don't reveal discipline-specific capabilities. EduArt provides a fine-grained benchmark to assess art historical knowledge, showing that format significantly affects performance."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
