{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24894", "kind": "paper", "url": "https://arxiv.org/abs/2606.24894"}, {"id": "gh:bftree/rwgbench", "kind": "repo", "url": "https://github.com/BFTree/RWGBench"}], "authors": ["Anzhe Xie", "Weihang Su", "Jiaxin Mao", "Yiqun Liu", "Min Zhang", "Shaoping Ma", "Qingyao Ai"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24894", "source_url": "https://arxiv.org/abs/2606.24894"}, "categories": ["General AI", "Language & Knowledge", "cs.DL"], "description": {"en": "Evaluates related work generation as citation-centric scholarly positioning. Uses 100 peer-reviewed papers and a 1.09M-document retrieval corpus, with metrics for citation selection, contextual appropriateness, organization, and discourse structure."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24894", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24894", "title": "RWGBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University", "Renmin University of China"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24894", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24894", "source_url": "https://openalex.org/W7165866986"}, "key": "claire-radar:2606.24894", "modality": null, "name": "RWGBench", "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_rwgbench_ed2b1ef6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ab54dff579cfef525c50c8da18a4a550342dfd04b73c8a3079250e56c708e2a8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24894"}, "publisher": null, "released": "2026-05-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24894", "source_url": "https://arxiv.org/abs/2606.24894"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24894", "source": "claire_radar", "source_benchmark_id": "2606.24894", "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/BFTree/RWGBench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.24894", "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": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "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": "a1ecf362651ed4c768e7728026c03a125a995cfb2be63e634041548dbc9f88dc", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates related work generation as citation-centric scholarly positioning. Uses 100 peer-reviewed papers and a 1.09M-document retrieval corpus, with metrics for citation selection, contextual appropriateness, organization, and discourse structure.", "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": "However, related work writing is fundamentally a citation-level scholarly positioning task: it requires selecting, organizing, and framing prior work to clarify how a target paper relates to, differs from, and contributes beyond existing research.As a result, models may generate coherent and semantically-relevant text while exhibiting academically critical failures, such as inappropriate citation selection or misplaced references, that conventional metrics do not capture.To this end, we introduc"}, "familyId": "bmf_9188a660e3ea", "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/BFTree/RWGBench", "url": "https://github.com/BFTree/RWGBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/BFTree/RWGBench", "url": "https://huggingface.co/papers/2606.24894"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/BFTree/RWGBench", "url": "https://arxiv.org/abs/2606.24894"}], "scope": "benchmark_repo", "url": "https://github.com/BFTree/RWGBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_rwgbench_ed2b1ef6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/BFTree/RWGBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.24894", "paper": "https://arxiv.org/abs/2606.24894", "pdf": "https://arxiv.org/pdf/2606.24894", "project": null, "report": "https://arxiv.org/abs/2606.24894"}, "metrics": [], "motivation": "Large language models have shown strong fluency in scientific writing, yet the evaluation of related work generation (RWG) remains limited.", "name": "RWGBench", "oneLine": "Evaluates related work generation as citation-centric scholarly positioning. Uses 100 peer-reviewed papers and a 1.09M-document retrieval corpus, with metrics for citation selection, contextual appropriateness, organization, and discourse structure.", "paperTitle": "RWGBench: Evaluating Scholarly Positioning in Related Work Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24894", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-30", "source": {"authors": ["Anzhe Xie", "Weihang Su", "Jiaxin Mao", "Yiqun Liu", "Min Zhang", "Shaoping Ma", "Qingyao Ai"], "categories": ["cs.DL", "cs.AI"], "id": "2606.24894", "title": "RWGBench: Evaluating Scholarly Positioning in Related Work Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24894"}, "sourceUpdatedAt": "2026-07-29T17:31:11Z", "topics": ["cs.DL"], "venueAttempts": [], "whyItMatters": "Fills the gap in RWG evaluation that relies on surface text similarity, offering a citation-centric testbed that aligns with expert judgment and reveals systematic limitations in current systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
