{"record": {"aliases": ["RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models"], "artifacts": [{"id": "arxiv:2608.26832", "kind": "paper", "url": "https://arxiv.org/abs/2608.26832"}, {"id": "gh:sharkspicy-nlp/ruleweaver", "kind": "repo", "url": "https://github.com/SharkSpicy-NLP/RuleWeaver"}], "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "RuleWeaver evaluates rule-centered scenario reasoning through scenario QA instances built from IF-THEN rules, with scoring based on answer correctness, rubric-based quality, rule recall, and rule precision."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.26832", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.26832", "title": "RuleWeaver"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.26832", "modality": null, "name": "RuleWeaver", "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": "true", "origin_record_id": "bm_ruleweaver-benchmarking-rule-centered-scen_2379b2dc", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "63a94c068d083dce3c1ba0e8a4010ffb879811a07571aeb99da112fcec46e32a", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-08T08:58:25.506689Z", "source_url": "https://arxiv.org/abs/2608.26832"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.26832", "source_url": "https://arxiv.org/abs/2608.26832"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-26832", "source": "claire_radar", "source_benchmark_id": "2608.26832", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-08", "attemptedAt": "2026-09-08T01:38:09.842216Z", "githubRepo": "https://github.com/SharkSpicy-NLP/RuleWeaver", "githubScope": "benchmark_repo", "githubStars": 28, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.26832", "observedAt": "2026-09-08T01:38:09.842216Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-08T01:38:09.842216Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-09-08T01:38:09.842216Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark targets an underexplored reasoning aspect and provides code plus dataset, likely attracting NLP community interest, though the topic is niche.", "score": 65}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:58:25.506689Z", "inputHash": "deee126a411d4da3f5d8b8a6ce5c0faca3140d527cddbb32c7c2e540fe6ebf82", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark has a formal name, code and dataset are publicly available, and it defines clear scoring metrics for repeated evaluation.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-08T08:58:25.506689Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RuleWeaver evaluates rule-centered scenario reasoning through scenario QA instances built from IF-THEN rules, with scoring based on answer correctness, rubric-based quality, rule recall, and rule precision.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "To address these gaps, this paper introduces RuleWeaver, a benchmark construction framework for evaluating rule-centered scenario reasoning."}, "familyId": "bmf_5a6c19eca015", "firstSeenAt": "2026-08-30", "heat": null, "id": "bm_ruleweaver-benchmarking-rule-centered-scen_2379b2dc", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": "https://github.com/SharkSpicy-NLP/RuleWeaver", "data": null, "paper": "https://arxiv.org/abs/2608.26832", "pdf": "https://arxiv.org/pdf/2608.26832", "project": null, "report": "https://arxiv.org/abs/2608.26832"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly applied to specialized domains, where effective use of domain expertise often requires reasoning over complex rules in concrete scenarios.", "name": "RuleWeaver", "oneLine": "RuleWeaver evaluates rule-centered scenario reasoning through scenario QA instances built from IF-THEN rules, with scoring based on answer correctness, rubric-based quality, rule recall, and rule precision.", "paperTitle": "RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by EMNLP 2026 Findings", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.26832", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 Findings", "verifiedAt": "2026-08-30T06:59:55.242506Z"}, "publications": [], "publishers": [{"name": "SharkSpicy-NLP", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/SharkSpicy-NLP/RuleWeaver"}], "ranking": {"30d": {"confidence": "High", "coverage": 0.85, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.5015207485401589, "value": 28}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "High", "coverage": 0.85, "rank": 69, "score": 35}, "method": "attention-ranking-v13", "rank": 69, "score": 35}, "90d": {"confidence": "Medium", "coverage": 0.7, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.45500181975044757, "value": 28}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.7, "rank": 136, "score": 40}, "method": "attention-ranking-v13", "rank": 136, "score": 40}}, "readiness": "Runnable", "recognitionConfidence": 0.55, "relation": "evaluates_only", "releasedAt": "2026-08-27", "source": {"authors": ["Bohan Yu", "Shi-Yang Li", "Pengfei Cao", "Jun Zhao", "Kang Liu"], "categories": ["cs.CL"], "id": "2608.26832", "title": "RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.26832"}, "sourceUpdatedAt": "2026-08-27T09:05:11Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted by EMNLP 2026 Findings", "evidence": [{"level": "author-claim", "observedAt": "2026-08-30T06:59:55.242506Z", "rawValue": "Accepted by EMNLP 2026 Findings", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.26832"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 Findings"}], "whyItMatters": "It addresses the gap in benchmarks that overlook the role of rules in scenario reasoning, offering process-level metrics to distinguish models' rule understanding beyond final answers."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
