{"record": {"aliases": [], "artifacts": [{"id": "gh:guptabhishekumar/grit-benchmark", "kind": "repo", "url": "https://github.com/guptabhishekumar/grit-benchmark"}, {"kind": "website", "url": "https://mujoco.org"}], "categories": ["Robotics", "Robotics & Embodied AI"], "description": {"en": "Evaluates LLM planners on robot skill execution under turbulence, scoring recovery from disruptions across tasks, tiers, and seeds."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/guptabhishekumar/grit-benchmark", "source": "claire_radar", "source_url": "https://github.com/guptabhishekumar/grit-benchmark", "title": "GRIT"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:guptabhishekumar/grit-benchmark", "modality": null, "name": "GRIT", "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-candidate", "display_eligible": "false", "origin_record_id": "bm_grit-benchmark_0cf59789", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "89bd25664c00afc3bfb59804a4d7eb6230f972807f69baf98dda1cd5d95e63e1", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-25T23:28:56.873215Z", "source_url": "https://github.com/guptabhishekumar/grit-benchmark"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:guptabhishekumar/grit-benchmark", "source_url": "https://github.com/guptabhishekumar/grit-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-guptabhishekumar-grit-benchmark", "source": "claire_radar", "source_benchmark_id": "github:guptabhishekumar/grit-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/guptabhishekumar/grit-benchmark", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "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": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Robot turbulence benchmarking is a specialized but emerging area, and the repository provides a complete harness and results, though frontier-model adoption is pending.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T23:28:56.873215Z", "inputHash": "e11231de7e4841e9e486639d8b23905682df962dd3430327b64d1a99be027266", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The formal benchmark name is source-grounded, but the public release does not yet meet the independent evidence or adoption threshold.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T23:28:56.873215Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates LLM planners on robot skill execution under turbulence, scoring recovery from disruptions across tasks, tiers, and seeds.", "discoverySources": [{"id": "github:guptabhishekumar/grit-benchmark", "type": "github", "url": "https://github.com/guptabhishekumar/grit-benchmark"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "grit-benchmark GRIT: a benchmark scoring LLM planners that drive robot skills while the world undoes their work."}, "familyId": "bmf_39727565f571", "firstSeenAt": "2026-08-24", "heat": null, "id": "bm_grit-benchmark_0cf59789", "indexedAt": "2026-08-24T07:04:32.475961Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/guptabhishekumar/grit-benchmark", "project": "https://mujoco.org"}, "metrics": [], "motivation": "grit-benchmark GRIT: a benchmark scoring LLM planners that drive robot skills while the world undoes their work.", "name": "GRIT", "oneLine": "Evaluates LLM planners on robot skill execution under turbulence, scoring recovery from disruptions across tasks, tiers, and seeds.", "paperTitle": "grit-benchmark", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/guptabhishekumar/grit-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-24T07:04:32.475961Z"}, "publications": [], "publishers": [{"name": "GRIT authors", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/guptabhishekumar/grit-benchmark"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 498, "score": 23}, "method": "attention-ranking-v13", "rank": 498, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-22", "source": {"authors": ["guptabhishekumar"], "categories": [], "id": "github:guptabhishekumar/grit-benchmark", "title": "grit-benchmark", "type": "github", "url": "https://github.com/guptabhishekumar/grit-benchmark"}, "sourceUpdatedAt": "2026-08-23T16:22:35Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Moves robot planning evaluation from clean execution to recovery under adversarial conditions, distinguishing robust planners from those that only verify."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
