{"record": {"aliases": ["Embodied-Bench"], "artifacts": [{"id": "arxiv:2609.13082", "kind": "paper", "url": "https://arxiv.org/abs/2609.13082"}], "categories": ["Robotics & Embodied AI", "cs.AI"], "description": {"en": "Embodied-BenchForge is an agentic workflow that transforms user-specified evaluation intents into embodied benchmark artifacts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.13082", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.13082", "title": "Embodied-BenchForge"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.13082", "modality": null, "name": "Embodied-BenchForge", "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_embodied-bench_5c4c02cd", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "63d06570b010384aed4326c345d5ac2b339b1bfb839173cf57bf7675bedaf4ed", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T10:05:20.149847Z", "source_url": "https://arxiv.org/abs/2609.13082"}, "publisher": null, "released": "2026-09-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.13082", "source_url": "https://arxiv.org/abs/2609.13082"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-13082", "source": "claire_radar", "source_benchmark_id": "2609.13082", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Embodied-Bench"], "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/2609.13082", "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": "The source presents an agentic benchmark-construction workflow rather than a releasable benchmark, with no artifacts or evaluation contract supplied.", "score": 0}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-15T09:37:10.086794Z", "inputHash": "c6ccac2ddd8314bcc4ae01564bdd52abb3fd506efabc84b4429490aa268e386a", "model": "deepseek-v4-flash"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction", "canonicalNameSource": "paper_title", "decisionReason": "Insufficient evidence of a released benchmark with defined tasks, scoring, and public reuse path.", "evaluationEvidence": {"reuse": "Quality assessment and ablations validate benchmark quality and the effectiveness of verification and repair, while repair and skill-reuse analyses demonstrate efficient localized recovery and cross-benchmark reusability.", "scoring": "Evaluations of representative MLLMs and embodied agents show that the benchmarks distinguish model capabilities in both observation-based understanding and closed-loop execution.", "task": "Constructs six benchmarks covering diverse embodied scenarios in the Offline EQA Track, together with one interactive benchmark containing 220 executable tasks in the Interactive Embodied Track."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-14T10:05:20.149847Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Embodied-BenchForge is an agentic workflow that transforms user-specified evaluation intents into embodied benchmark artifacts.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We present Embodied-BenchForge, an agentic framework that transforms user-specified evaluation intents into complete embodied benchmark artifacts."}, "familyId": "bmf_494a81e5eb85", "firstSeenAt": "2026-09-14", "heat": null, "id": "bm_embodied-bench_5c4c02cd", "indexedAt": "2026-09-14T06:39:43.852630Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.13082", "pdf": "https://arxiv.org/pdf/2609.13082", "project": null, "report": "https://arxiv.org/abs/2609.13082"}, "metrics": [], "motivation": "Agentic systems offer a promising way to automate embodied benchmark construction, but existing approaches typically cover isolated stages or remain specialized to predefined environments and task families.", "name": "Embodied-BenchForge", "oneLine": "Embodied-BenchForge is an agentic workflow that transforms user-specified evaluation intents into embodied benchmark artifacts.", "paperTitle": "Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.13082", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-14T06:39:43.852630Z"}, "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": 0.55, "relation": "evaluates_only", "releasedAt": "2026-09-11", "source": {"authors": ["Baoyang Jiang", "Fengchun Zhang", "Leyuan Wang", "Haotian Li", "Yida Wang", "Zhe Ji", "Jinshan Lai", "Xi Ren", "Danyang Li", "Zheng Yang", "Jianwei Hu", "and Qiang Ma"], "categories": ["cs.AI"], "id": "2609.13082", "title": "Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction", "type": "arxiv", "url": "https://arxiv.org/abs/2609.13082"}, "sourceUpdatedAt": "2026-09-11T17:16:01Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Automating benchmark construction for embodied evaluation could reduce the labor of building task suites, but this source describes a construction framework rather than a benchmark itself."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
