{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.22990", "kind": "paper", "url": "https://arxiv.org/abs/2608.22990v1"}, {"id": "gh:horizonrobotics/roboorchardsim", "kind": "repo", "url": "https://github.com/HorizonRobotics/RoboOrchardSim"}], "authors": ["Mengao Zhao", "Ziang Li", "Chaodong Huang", "Mengchen Ma", "Haoyi Jiang", "Yiwei Jin", "Xinjie Wang", "Yun Du", "Xuewu Lin", "Taojun Ding", "Hongyu Xie", "Jackson Jiang", "Chunlei Yu", "Kaihua Zhang", "Lichao Huang", "Liu Liu", "Tianwei Lin", "Zhizhong Su"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.22990", "source_url": "https://arxiv.org/abs/2608.22990"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "Evaluates instruction-following in robot manipulation through pick-and-place tasks requiring language grounding across category, attribute, spatial, and compositional skills."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.22990v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.22990v1", "title": "InstructMove"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.22990", "modality": null, "name": "InstructMove", "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_instructmove_3a1c4064", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3f7d418512ebebc796451dde6a767b8ce202a0022b21ddf18c6da639205e5044", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.22990v1"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.22990", "source_url": "https://arxiv.org/abs/2608.22990v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-22990", "source": "claire_radar", "source_benchmark_id": "2608.22990", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T16:48:55.714492Z", "githubRepo": "https://github.com/HorizonRobotics/RoboOrchardSim", "githubScope": "benchmark_repo", "githubStars": 11, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.22990", "observedAt": "2026-08-25T16:48:55.714492Z", "signalStatus": {"githubStars": {"observedAt": "2026-08-25T16:48:55.714492Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T16:48:55.714492Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark targets an important limitation in robotics instruction following and offers simulation assets with public code, likely to attract attention from embodied AI researchers.", "score": 62}, "capabilities": ["Robot manipulation"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:18:56.318436Z", "inputHash": "6a7dd22fb166ed396df4583c685df542a882c1c9957ae96efdb23db062f2eeb4", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce InstructMove, a text-indispensable benchmark for instruction-following manipulation.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is formally introduced with a clear train-eval protocol, held-out tasks, and public code, enabling reuse and comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates instruction-following in robot manipulation through pick-and-place tasks requiring language grounding across category, attribute, spatial, and compositional skills.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce InstructMove, a text-indispensable benchmark for instruction-following manipulation."}, "familyId": "bmf_a776350d9ba4", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_instructmove_3a1c4064", "indexedAt": "2026-08-25T16:21:05.134052Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/HorizonRobotics/RoboOrchardSim", "data": null, "paper": "http://arxiv.org/abs/2608.22990v1", "pdf": "https://arxiv.org/pdf/2608.22990v1", "project": null, "report": "http://arxiv.org/abs/2608.22990v1"}, "metrics": [], "motivation": "Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions.", "name": "InstructMove", "oneLine": "Evaluates instruction-following in robot manipulation through pick-and-place tasks requiring language grounding across category, attribute, spatial, and compositional skills.", "paperTitle": "InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.22990v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T16:21:05.134052Z"}, "publications": [], "publishers": [{"name": "Horizon Robotics", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/HorizonRobotics/RoboOrchardSim"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": 0.8120300751879699, "value": 11}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 35, "score": 67}, "method": "attention-ranking-v11", "rank": 35, "score": 67}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": 0.6782729805013927, "value": 11}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 130, "score": 60}, "method": "attention-ranking-v11", "rank": 130, "score": 60}, "today": {"confidence": "Medium", "coverage": 0.7, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}, "llmAttentionForecast": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 2, "historyDate": "2026-08-24", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"percentile": 0.875, "value": 11}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}, "llmAttentionForecast": {"percentile": 0.4, "value": 40}}, "confidence": "Medium", "coverage": 0.7, "rank": 1, "score": 57}, "method": "attention-ranking-v11", "rank": 1, "score": 57}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Mengao Zhao", "Ziang Li", "Chaodong Huang", "Mengchen Ma", "Haoyi Jiang", "Yiwei Jin", "Xinjie Wang", "Yun Du", "Xuewu Lin", "Taojun Ding", "Hongyu Xie", "Jackson Jiang", "Chunlei Yu", "Kaihua Zhang", "Lichao Huang", "Liu Liu", "Tianwei Lin", "Zhizhong Su"], "categories": ["cs.RO"], "id": "2608.22990", "title": "InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation", "type": "arxiv", "url": "http://arxiv.org/abs/2608.22990v1"}, "sourceUpdatedAt": "2026-08-24T08:53:41Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Provides a controlled testbed to diagnose visual shortcut learning in vision-language-action policies, improving reliability of language-conditioned manipulation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
