{"record": {"aliases": ["Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation"], "artifacts": [{"id": "arxiv:2609.08209", "kind": "paper", "url": "https://arxiv.org/abs/2609.08209"}, {"kind": "website", "url": "https://roboreel.github.io"}], "authors": ["Weiwei Gu", "Anmol Gupta", "Anant Sah", "Ryan Varghese", "Lalitha Shreya Vanam", "Prabhath Adireddi", "Peter Karkus", "Nakul Gopalan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.08209", "source_url": "https://arxiv.org/abs/2609.08209"}, "categories": ["Robotics", "Robotics & Embodied AI"], "description": {"en": "Benchmark for robot learning from observation using real human videos, simulated trajectories, and evaluation environments across ten tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.08209", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.08209", "title": "RoboReel"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.08209", "modality": null, "name": "RoboReel", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_monkey-see-can-monkey-do-a-benchmark-for-e_8799e891", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "ce4c5535cedb1618dd99e41ae7e6e439456c6b6787e83f7bc1914801648d5219", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-09T09:06:08.213644Z", "source_url": "https://arxiv.org/abs/2609.08209"}, "publisher": null, "released": "2026-09-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.08209", "source_url": "https://arxiv.org/abs/2609.08209"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-08209", "source": "claire_radar", "source_benchmark_id": "2609.08209", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation"], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2609.08209", "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", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Robotics benchmark topic has moderate interest, but lack of accessible artifacts likely limits early attention.", "score": 35}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T09:06:08.213644Z", "inputHash": "023f9994f67f0be3dc13cd7efa7da7bff00c349ac45969c62c8cab3f97e02f76", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "we introduce RoboReel: a unified benchmark for evaluating models that learn policies from human videos.", "canonicalNameSource": "abstract", "decisionReason": "No artifact evidence or code/data links provided in the input; cannot verify task definition or scoring protocol.", "evaluationEvidence": {"reuse": "Webpage: https://roboreel.github.io", "scoring": "Four test suites evaluate robustness to visual distractors and long-horizon task completion, with studies covering over seven state-of-the-art algorithms.", "task": "Evaluate models that learn robot manipulation policies from human demonstration videos on ten real-world tasks, with bundled human videos, simulated robot trajectories, and evaluation environments."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T09:06:08.213644Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Benchmark for robot learning from observation using real human videos, simulated trajectories, and evaluation environments across ten tasks.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address these challenges, we introduce RoboReel: a unified benchmark for evaluating models that learn policies from human videos."}, "familyId": "bmf_ff3d40ed51fb", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_monkey-see-can-monkey-do-a-benchmark-for-e_8799e891", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.08209", "pdf": "https://arxiv.org/pdf/2609.08209", "project": "https://roboreel.github.io", "report": "https://arxiv.org/abs/2609.08209"}, "metrics": [], "motivation": "Learning from Observation (LfO) is a fundamental robotic capability that replicates how humans and animals socially learn from each other.", "name": "RoboReel", "oneLine": "Benchmark for robot learning from observation using real human videos, simulated trajectories, and evaluation environments across ten tasks.", "paperTitle": "Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.08209", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-09-08", "source": {"authors": ["Weiwei Gu", "Anmol Gupta", "Anant Sah", "Ryan Varghese", "Lalitha Shreya Vanam", "Prabhath Adireddi", "Peter Karkus", "Nakul Gopalan"], "categories": ["cs.RO"], "id": "2609.08209", "title": "Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation", "type": "arxiv", "url": "https://arxiv.org/abs/2609.08209"}, "sourceUpdatedAt": "2026-09-08T03:48:44Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Aims to standardize evaluation of learning-from-observation methods, addressing variability in assumptions and hardware."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
