{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.12071", "kind": "paper", "url": "https://arxiv.org/abs/2606.12071"}], "authors": ["Soumitra Sinhahajari", "Navonil Majumder", "Soujanya Poria"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.12071", "source_url": "https://arxiv.org/abs/2606.12071"}, "categories": ["General AI", "Language & Knowledge", "cs.DL"], "description": {"en": "RQ-Bench evaluates novelty of research questions generated by LLMs against author-anchored reference questions from recent arXiv papers, using standalone and comparative LLM judging as well as human expert evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.12071", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.12071", "title": "RQ-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Nanyang Technological University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.12071", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.12071", "source_url": "https://openalex.org/W7164379171"}, "key": "claire-radar:2606.12071", "modality": null, "name": "RQ-Bench", "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": "unknown", "origin_record_id": "bm_rq-bench_0360bc38", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "c4127485d23f4b9e486b27be73e4dea424df032ca2872172eb6d45a3abcbda61", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.12071"}, "publisher": null, "released": "2026-06-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.12071", "source_url": "https://arxiv.org/abs/2606.12071"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-12071", "source": "claire_radar", "source_benchmark_id": "2606.12071", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "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": 2, "hfPaperUrl": "https://huggingface.co/papers/2606.12071", "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", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "8e03f9b7c9de33ce9f875f99b46d0b781095724daff49d7d062b1b2e5c6ba26a", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RQ-Bench evaluates novelty of research questions generated by LLMs against author-anchored reference questions from recent arXiv papers, using standalone and comparative LLM judging as well as human expert evaluation.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "We introduce RQ-Bench, a benchmark built from recent arXiv papers."}, "familyId": "bmf_c9112d4b22f3", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_rq-bench_0360bc38", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.12071", "paper": "https://arxiv.org/abs/2606.12071", "pdf": "https://arxiv.org/pdf/2606.12071", "project": null, "report": "https://arxiv.org/abs/2606.12071"}, "metrics": [], "motivation": "LLMs are increasingly used to generate and judge scientific ideas.", "name": "RQ-Bench", "oneLine": "RQ-Bench evaluates novelty of research questions generated by LLMs against author-anchored reference questions from recent arXiv papers, using standalone and comparative LLM judging as well as human expert evaluation.", "paperTitle": "On the Limits of LLM-as-Judge for Scientific Novelty Assessment", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.12071", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-10", "source": {"authors": ["Soumitra Sinhahajari", "Navonil Majumder", "Soujanya Poria"], "categories": ["cs.DL", "cs.AI"], "id": "2606.12071", "title": "On the Limits of LLM-as-Judge for Scientific Novelty Assessment", "type": "arxiv", "url": "https://arxiv.org/abs/2606.12071"}, "sourceUpdatedAt": "2026-06-10T13:34:38Z", "topics": ["cs.DL"], "venueAttempts": [], "whyItMatters": "Addresses the reliability of LLM-based novelty assessment for scientific ideation, indicating that LLM judges may produce a 'novelty mirage' compared to human experts. Useful for researchers evaluating automated scientific review or generation systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
