{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.22678", "kind": "paper", "url": "https://arxiv.org/abs/2606.22678"}], "authors": ["Meher Bhaskar Madiraju", "Meher Sai Preetam Madiraju"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.22678", "source_url": "https://arxiv.org/abs/2606.22678"}, "categories": ["Agents & Tool Use", "Software & AI Compute", "cs.SE"], "description": {"en": "RigorBench evaluates autonomous AI coding agents on engineering process discipline across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. It includes 30 tasks in five categories and a composite RigorScore metric."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.22678", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.22678", "title": "RigorBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.22678", "modality": null, "name": "RigorBench", "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_rigorbench_122c9d4f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "64bd1dc98ff0c784c9eec679a38cd71b2a599967f9fd94b9e172d498f68cf68d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.22678"}, "publisher": null, "released": "2026-06-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.22678", "source_url": "https://arxiv.org/abs/2606.22678"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-22678", "source": "claire_radar", "source_benchmark_id": "2606.22678", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Software & AI Compute"], "area": "Agents & Tool Use", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.22678", "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": "2026-10-04", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b307b8177198c0f9921172b8e9e4fc4c0170e57c3b449c8940f317cd19278d17", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RigorBench evaluates autonomous AI coding agents on engineering process discipline across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. It includes 30 tasks in five categories and a composite RigorScore metric.", "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"], "snippet": "We introduce RigorBench, the first benchmark designed to measure process discipline in AI coding agents."}, "familyId": "bmf_41aa52836b4e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_rigorbench_122c9d4f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.22678", "paper": "https://arxiv.org/abs/2606.22678", "pdf": "https://arxiv.org/pdf/2606.22678", "project": null, "report": "https://arxiv.org/abs/2606.22678"}, "metrics": [], "motivation": "Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks.", "name": "RigorBench", "oneLine": "RigorBench evaluates autonomous AI coding agents on engineering process discipline across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. It includes 30 tasks in five categories and a composite RigorScore metric.", "paperTitle": "RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.22678", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-21", "source": {"authors": ["Meher Bhaskar Madiraju", "Meher Sai Preetam Madiraju"], "categories": ["cs.SE", "cs.AI"], "id": "2606.22678", "title": "RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.22678"}, "sourceUpdatedAt": "2026-06-29T19:02:41Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Existing agent benchmarks focus on outcome correctness, ignoring process quality. RigorBench fills this gap by measuring how agents plan, verify, and recover, providing a more comprehensive assessment for reliable deployment in real-world software engineering."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
