{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.04646", "kind": "paper", "url": "https://arxiv.org/abs/2606.04646"}, {"id": "gh:zhang-mengao/qo-bench", "kind": "repo", "url": "https://github.com/ZHANG-MENGAO/qo-bench"}], "authors": ["Mengao Zhang", "Xiang Yang", "Chang Liu", "Tianhui Tan", "Ke-wei Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.04646", "source_url": "https://arxiv.org/abs/2606.04646"}, "categories": ["General AI", "Information retrieval", "Language & Knowledge", "cs.CL"], "description": {"en": "QO-Bench is a diagnostic benchmark for query-operator question answering over typed event tuples. It covers 22,984 news articles, 614 corporate events, and 18 query templates, with 785 questions. Gold answers are deterministically computed and scored by recall via exact match."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.04646", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.04646", "title": "QO-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.04646", "modality": null, "name": "QO-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_qo-bench_a8720b3c", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "ac266e651fd51b914f7d90816dc62bd493c32ced46e705af3169c672117b39b2", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.04646"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.04646", "source_url": "https://arxiv.org/abs/2606.04646"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-04646", "source": "claire_radar", "source_benchmark_id": "2606.04646", "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": "https://github.com/ZHANG-MENGAO/qo-bench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.04646", "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": ["Information retrieval"], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "48fb9c248162a794fe7dccec2e9caf8dbdf5ea3edd84a9cc951e9d33183517df", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "QO-Bench is a diagnostic benchmark for query-operator question answering over typed event tuples. It covers 22,984 news articles, 614 corporate events, and 18 query templates, with 785 questions. Gold answers are deterministically computed and scored by recall via exact match.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce QO-Bench, a diagnostic benchmark for query-operator question answering over typed event tuples."}, "familyId": "bmf_881e5bfa61b8", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-report", "linkedUrl": "https://github.com/ZHANG-MENGAO/qo-bench.", "url": "https://arxiv.org/abs/2606.04646"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/ZHANG-MENGAO/qo-bench", "url": "https://arxiv.org/abs/2606.04646"}], "scope": "benchmark_repo", "url": "https://github.com/ZHANG-MENGAO/qo-bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_qo-bench_a8720b3c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/ZHANG-MENGAO/qo-bench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.04646", "paper": "https://arxiv.org/abs/2606.04646", "pdf": "https://arxiv.org/pdf/2606.04646", "project": null, "report": "https://arxiv.org/abs/2606.04646"}, "metrics": [], "motivation": "Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text.", "name": "QO-Bench", "oneLine": "QO-Bench is a diagnostic benchmark for query-operator question answering over typed event tuples. It covers 22,984 news articles, 614 corporate events, and 18 query templates, with 785 questions. Gold answers are deterministically computed and scored by recall via exact match.", "paperTitle": "QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to Findings of EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.04646", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Findings of EMNLP 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.04646"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Mengao Zhang", "Xiang Yang", "Chang Liu", "Tianhui Tan", "Ke-wei Huang"], "categories": ["cs.CL", "cs.AI", "cs.IR"], "id": "2606.04646", "title": "QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples", "type": "arxiv", "url": "https://arxiv.org/abs/2606.04646"}, "sourceUpdatedAt": "2026-06-03T09:14:43Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted to Findings of EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to Findings of EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.04646"}], "reviewStatus": "accepted", "venueName": "Findings of EMNLP 2026"}], "whyItMatters": "RAG systems may retrieve relevant passages but fail to preserve typed values needed for query operators. QO-Bench exposes this gap and allows operator-level diagnosis, guiding development of retrieval systems that preserve query semantics."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
