{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.08093", "kind": "paper", "url": "https://arxiv.org/abs/2607.08093"}, {"id": "gh:andleb/causalds", "kind": "repo", "url": "https://github.com/andleb/causalds"}], "authors": ["Andrej Leban", "Theo Saarinen", "Yuekai Sun"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.08093", "source_url": "https://arxiv.org/abs/2607.08093"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "Evaluates causal reasoning in data-science workflows using synthetic scenes with hidden structural causal models, covering Pearl's three rungs and abstention scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.08093", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.08093", "title": "CausalDS"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Michigan"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.08093", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.08093", "source_url": "https://openalex.org/W7167894926"}, "key": "claire-radar:2607.08093", "modality": null, "name": "CausalDS", "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_causalds_e9c95fdf", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9cea06fef80eaf72e1ce8d7f2604ae8d644ed9416f074b27b9efb706f980c1fd", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.08093"}, "publisher": null, "released": "2026-07-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.08093", "source_url": "https://arxiv.org/abs/2607.08093"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-08093", "source": "claire_radar", "source_benchmark_id": "2607.08093", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/andleb/causalds", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": "2026-07-10T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 5, "hfPaperUrl": "https://huggingface.co/papers/2607.08093", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "63fa98bc91ff1b80f07a3208683bc0c8a0b01b2787fa430a529bfa0994787fbf", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates causal reasoning in data-science workflows using synthetic scenes with hidden structural causal models, covering Pearl's three rungs and abstention scoring.", "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"], "snippet": "We introduce CausalDS, a benchmark for evaluating causal reasoning in agentic data-science workflows."}, "familyId": "bmf_c55169b2a8eb", "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/andleb/causalds", "url": "https://github.com/andleb/causalds"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/andleb/causalds", "url": "https://huggingface.co/papers/2607.08093"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/andleb/causalds", "url": "https://huggingface.co/api/papers/2607.08093"}], "scope": "benchmark_repo", "url": "https://github.com/andleb/causalds", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_causalds_e9c95fdf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/andleb/causalds", "data": null, "hfPaper": "https://huggingface.co/papers/2607.08093", "paper": "https://arxiv.org/abs/2607.08093", "pdf": "https://arxiv.org/pdf/2607.08093", "project": null, "report": "https://arxiv.org/abs/2607.08093"}, "metrics": [], "motivation": "Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use.", "name": "CausalDS", "oneLine": "Evaluates causal reasoning in data-science workflows using synthetic scenes with hidden structural causal models, covering Pearl's three rungs and abstention scoring.", "paperTitle": "CausalDS: Benchmarking Causal Reasoning in Data-Science Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.08093", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.31659423970600165, "value": 5}}, "confidence": "Medium", "coverage": 0.7, "rank": 291, "score": 28}, "method": "attention-ranking-v13", "rank": 291, "score": 28}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-09", "source": {"authors": ["Andrej Leban", "Yuekai Sun"], "categories": ["cs.AI", "cs.CL", "cs.LG"], "id": "2607.08093", "title": "CausalDS: Benchmarking Causal Reasoning in Data-Science Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2607.08093"}, "sourceUpdatedAt": "2026-07-09T04:03:26Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Bridges symbolic causal reasoning and realistic data analysis, providing a joint evaluation of reasoning, tool use, and uncertainty quantification in agentic settings."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
