{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01810", "kind": "paper", "url": "https://arxiv.org/abs/2606.01810"}, {"id": "gh:thusi-lab/causal-reasoner", "kind": "repo", "url": "https://github.com/THUSI-Lab/Causal-Reasoner"}], "authors": ["Zheng Lu", "Mingqi Gao", "Qinlei Xie", "Wanqi Zhong", "Hanwen Cui", "Zirui Song", "Lijie Wang", "Chong Luo", "Bei Liu", "Yiming Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01810", "source_url": "https://arxiv.org/abs/2606.01810"}, "categories": ["Planning", "Robotics & Embodied AI", "cs.AI"], "description": {"en": "Causal-Plan-Bench evaluates embodied planning across four causal dimensions (executability, effects, composition, robustness) using 1,200 instances from 12 tasks, with MCQ and rubric-based scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01810", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01810", "title": "Causal-Plan-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Microsoft Research Asia (China)", "Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01810", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01810", "source_url": "https://openalex.org/W7163165227"}, "key": "claire-radar:2606.01810", "modality": null, "name": "Causal-Plan-Bench", "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_causal-plan-bench_5fd0e720", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "24f07d71af4b85ac8ba5b8950b2c71c57f817fa3be402d4339073daee33ef682", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01810"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01810", "source_url": "https://arxiv.org/abs/2606.01810"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01810", "source": "claire_radar", "source_benchmark_id": "2606.01810", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/THUSI-Lab/Causal-Reasoner", "githubScope": "benchmark_repo", "githubStars": 6, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.01810", "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": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Planning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b360f841ae56a26306a2e458c474a28dfaf6d4539e212bdce2b7429ced9bd3f6", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Causal-Plan-Bench evaluates embodied planning across four causal dimensions (executability, effects, composition, robustness) using 1,200 instances from 12 tasks, with MCQ and rubric-based scoring.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To this end, we introduce Causal-Plan-Bench, a high-fidelity diagnostic suite curated through multi-stage verification to evaluate embodied planning across four causal dimensions."}, "familyId": "bmf_d4b6f2500fcb", "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/THUSI-Lab/Causal-Reasoner", "url": "https://github.com/THUSI-Lab/Causal-Reasoner"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/THUSI-Lab/Causal-Reasoner", "url": "https://huggingface.co/papers/2606.01810"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/THUSI-Lab/Causal-Reasoner", "url": "https://arxiv.org/abs/2606.01810"}], "scope": "project_repo", "url": "https://github.com/THUSI-Lab/Causal-Reasoner", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_causal-plan-bench_5fd0e720", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/THUSI-Lab/Causal-Reasoner", "data": null, "hfPaper": "https://huggingface.co/papers/2606.01810", "paper": "https://arxiv.org/abs/2606.01810", "pdf": "https://arxiv.org/pdf/2606.01810", "project": null, "report": "https://arxiv.org/abs/2606.01810"}, "metrics": [], "motivation": "Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning.", "name": "Causal-Plan-Bench", "oneLine": "Causal-Plan-Bench evaluates embodied planning across four causal dimensions (executability, effects, composition, robustness) using 1,200 instances from 12 tasks, with MCQ and rubric-based scoring.", "paperTitle": "Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01810", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "THUSI-Lab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/THUSI-Lab/Causal-Reasoner"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Zheng Lu", "Mingqi Gao", "Qinlei Xie", "Wanqi Zhong", "Hanwen Cui", "Heng Cao", "Zirui Song", "Yifan Yang", "Chong Luo", "Bei Liu", "Yiming Li"], "categories": ["cs.AI"], "id": "2606.01810", "title": "Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01810"}, "sourceUpdatedAt": "2026-06-01T07:27:39Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Targets the gap where benchmarks reward linguistic prediction over physical causal reasoning, offering a diagnostic protocol to assess genuine physical agency and support training for grounded planning."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
