{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.09389", "kind": "paper", "url": "https://arxiv.org/abs/2606.09389"}, {"id": "gh:foggpoy/lexrubric", "kind": "repo", "url": "https://github.com/foggpoy/LexRubric"}], "authors": ["Yifan Chen", "Haitao Li", "Yiran Hu", "Kaisong Song", "Jun Lin", "Yueyue Wu", "Qingyao Ai", "Min Zhang", "Yiqun Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.09389", "source_url": "https://arxiv.org/abs/2606.09389"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "LexRubric evaluates open-ended legal tasks in Chinese, with 649 instances from legal consultation and judicial examination. It includes 12,337 expert-written atomic scoring criteria under a six-dimensional framework, enabling fine-grained diagnostic evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.09389", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.09389", "title": "LexRubric"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.09389", "modality": null, "name": "LexRubric", "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_lexrubric_7a24242e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "539d897bd917e2215981da25b5f5f66a0c383fae30025161b1dd34bf0ee08632", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.09389"}, "publisher": null, "released": "2026-06-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.09389", "source_url": "https://arxiv.org/abs/2606.09389"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-09389", "source": "claire_radar", "source_benchmark_id": "2606.09389", "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/foggpoy/LexRubric", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.09389", "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": "56b0ecb68d99a353289d7c154ada1d195d40459f80b74ca556b558b82401028e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LexRubric evaluates open-ended legal tasks in Chinese, with 649 instances from legal consultation and judicial examination. It includes 12,337 expert-written atomic scoring criteria under a six-dimensional framework, enabling fine-grained diagnostic evaluation.", "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", "public artifact URL"], "snippet": "We introduce LexRubric, a rubric-based benchmark for evaluating open-ended Chinese legal tasks."}, "familyId": "bmf_8419445f9469", "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/foggpoy/LexRubric", "url": "https://github.com/foggpoy/LexRubric"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/foggpoy/LexRubric", "url": "https://huggingface.co/papers/2606.09389"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/foggpoy/LexRubric.", "url": "https://arxiv.org/abs/2606.09389"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/foggpoy/LexRubric", "url": "https://arxiv.org/abs/2606.09389"}], "scope": "benchmark_repo", "url": "https://github.com/foggpoy/LexRubric", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_lexrubric_7a24242e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/foggpoy/LexRubric", "data": null, "hfPaper": "https://huggingface.co/papers/2606.09389", "paper": "https://arxiv.org/abs/2606.09389", "pdf": "https://arxiv.org/pdf/2606.09389", "project": null, "report": "https://arxiv.org/abs/2606.09389"}, "metrics": [], "motivation": "As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses has become essential.", "name": "LexRubric", "oneLine": "LexRubric evaluates open-ended legal tasks in Chinese, with 649 instances from legal consultation and judicial examination. It includes 12,337 expert-written atomic scoring criteria under a six-dimensional framework, enabling fine-grained diagnostic evaluation.", "paperTitle": "LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP 2026 Main Conference", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.09389", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 Main Conference", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "LexRubric Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/foggpoy/LexRubric"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-08", "source": {"authors": ["Yifan Chen", "Haitao Li", "Yiran Hu", "Kaisong Song", "Jun Lin", "Yueyue Wu", "Qingyao Ai", "Min Zhang", "Yiqun Liu"], "categories": ["cs.CL"], "id": "2606.09389", "title": "LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2606.09389"}, "sourceUpdatedAt": "2026-06-08T12:04:47Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026 Main Conference", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to EMNLP 2026 Main Conference", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.09389"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 Main Conference"}], "whyItMatters": "Open-ended legal responses require fine-grained evaluation beyond exact matching. LexRubric provides rubric-based diagnostic assessment, showing distinct capability profiles across models and highlighting challenges in open-ended legal questions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
