{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.01600", "kind": "paper", "url": "https://arxiv.org/abs/2609.01600"}, {"id": "gh:sileod/cordis-bench", "kind": "repo", "url": "https://github.com/sileod/cordis-bench"}, {"id": "hf:sileod/cordis-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/sileod/cordis-bench"}], "authors": ["Damien Sileo", "Dimitri Kachler"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.01600", "source_url": "https://arxiv.org/abs/2609.01600"}, "categories": ["Agents", "General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "Evaluates language models on reasoning about component lifecycle changes in dynamic agent harnesses via 1,200 questions covering localization, prediction, conditions, and reconfiguration."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.01600", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.01600", "title": "CordisBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Centre National de la Recherche Scientifique", "Institut national de recherche en sciences et technologies du numérique", "Université de Lille", "Centre de Recherche en Informatique, Signal et Automatique de Lille", "Centrale Lille Institut"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.01600", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.01600", "source_url": "https://openalex.org/W7206176552"}, "key": "claire-radar:2609.01600", "modality": null, "name": "CordisBench", "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": "true", "origin_record_id": "bm_cordisbench_3da54bce", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f0f21d93bc8a08490574022d283428fdbe69cb5a60b1facfe3199033f47170c6", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2609.01600"}, "publisher": null, "released": "2026-09-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.01600", "source_url": "https://arxiv.org/abs/2609.01600"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-01600", "source": "claire_radar", "source_benchmark_id": "2609.01600", "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/sileod/cordis-bench", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": "sileod/cordis-bench", "hfDatasetDownloads": 121, "hfDatasetLikes": 2, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.01600", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Well-documented benchmark with both code and data public, addressing emerging agent reasoning topics.", "score": 60}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "e66fc0e59a511b1e701732de35c9416276fbffa0047270f38b5a71ded9bf3bc6", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?", "canonicalNameSource": "paper_title", "decisionReason": "Code and data are available with clear instructions, deterministic scoring, and a frozen dataset; the benchmark supports ongoing model comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates language models on reasoning about component lifecycle changes in dynamic agent harnesses via 1,200 questions covering localization, prediction, conditions, and reconfiguration.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce CordisBench, a 1,200-question benchmark of this lifecycle reasoning."}, "familyId": "bmf_877808d3db35", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_cordisbench_3da54bce", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": "https://github.com/sileod/cordis-bench", "data": "https://huggingface.co/datasets/sileod/cordis-bench", "paper": "https://arxiv.org/abs/2609.01600", "pdf": "https://arxiv.org/pdf/2609.01600", "project": null, "report": "https://arxiv.org/abs/2609.01600"}, "metrics": [], "motivation": "Dynamic agent harnesses let language models change the software that shapes their own execution.", "name": "CordisBench", "oneLine": "Evaluates language models on reasoning about component lifecycle changes in dynamic agent harnesses via 1,200 questions covering localization, prediction, conditions, and reconfiguration.", "paperTitle": "CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.01600", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "publishers": [{"name": "CordisBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/sileod/cordis-bench"}], "ranking": {"90d": {"confidence": "High", "coverage": 0.85, "datasetDownloadRank": 54, "datasetRankPopulation": 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": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.4947177167171287, "value": 121}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "High", "coverage": 0.85, "rank": 274, "score": 30}, "method": "attention-ranking-v13", "rank": 274, "score": 30}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-01", "source": {"authors": ["Damien Sileo and Dimitri Kachler"], "categories": ["cs.CL", "cs.AI"], "id": "2609.01600", "title": "CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?", "type": "arxiv", "url": "https://arxiv.org/abs/2609.01600"}, "sourceUpdatedAt": "2026-09-01T17:59:13Z", "topics": ["Agents", "Reasoning"], "venueAttempts": [], "whyItMatters": "Measures a critical reasoning capability for agent harness safety and reliability, with deterministic scoring and executable answers enabling fair comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
