{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.16178", "kind": "paper", "url": "https://arxiv.org/abs/2606.16178"}, {"id": "gh:shahrutav/remembench", "kind": "repo", "url": "https://github.com/ShahRutav/ReMemBench"}, {"kind": "website", "url": "https://shahrutav.github.io/short-term-memory"}], "authors": ["Rutav Shah", "Rajat Kumar Jenamani", "Xiaohan Zhang", "Lingfeng Sun", "Roberto Martín-Martín", "Yuke Zhu", "Deva Ramanan", "Karl Schmeckpeper"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.16178", "source_url": "https://arxiv.org/abs/2606.16178"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "ReMemBench is a benchmark with eight diverse household manipulation tasks across four categories of short-term memory, designed to evaluate memory mechanisms in visuomotor policies."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.16178", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.16178", "title": "ReMemBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.16178", "modality": null, "name": "ReMemBench", "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_remembench_10890c1e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5fb50dd2e3dd2d8a0659476bbaf08c39e4cb9178049cee2a00df908fe8fd5d9a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.16178"}, "publisher": null, "released": "2026-06-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.16178", "source_url": "https://arxiv.org/abs/2606.16178"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-16178", "source": "claire_radar", "source_benchmark_id": "2606.16178", "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/ShahRutav/ReMemBench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.16178", "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", "state": "unavailable"}}, "status": "fresh"}, "capabilities": ["Robot manipulation"], "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": "d050cfd6b7237b105bd4bc8089a78db5df54dacfd5a7061f8bf6e926c5336108", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ReMemBench is a benchmark with eight diverse household manipulation tasks across four categories of short-term memory, designed to evaluate memory mechanisms in visuomotor policies.", "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 systematically evaluate memory in visuomotor control, we introduce ReMemBench -- a benchmark of eight diverse household manipulation tasks spanning four categories of short-term memory -- designed to foster general memory mechanisms rather than siloed, task-specific solutions."}, "familyId": "bmf_c308a8d726bb", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/ShahRutav/ReMemBench", "url": "https://shahrutav.github.io/short-term-memory"}], "scope": "benchmark_repo", "url": "https://github.com/ShahRutav/ReMemBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_remembench_10890c1e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/ShahRutav/ReMemBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.16178", "paper": "https://arxiv.org/abs/2606.16178", "pdf": "https://arxiv.org/pdf/2606.16178", "project": "https://shahrutav.github.io/short-term-memory", "report": "https://arxiv.org/abs/2606.16178"}, "metrics": [], "motivation": "Many robotic tasks require short-term memory, whether it's retrieving an object that's no longer visible or turning off an appliance after a set period.", "name": "ReMemBench", "oneLine": "ReMemBench is a benchmark with eight diverse household manipulation tasks across four categories of short-term memory, designed to evaluate memory mechanisms in visuomotor policies.", "paperTitle": "Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.16178", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "PRISM team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://shahrutav.github.io/short-term-memory"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-15", "source": {"authors": ["Rutav Shah", "Rajat Kumar Jenamani", "Xiaohan Zhang", "Lingfeng Sun", "Roberto Mart\\'in-Mart\\'in", "Yuke Zhu", "Deva Ramanan", "Karl Schmeckpeper"], "categories": ["cs.RO"], "id": "2606.16178", "title": "Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2606.16178"}, "sourceUpdatedAt": "2026-06-15T03:49:23Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "ReMemBench addresses the lack of systematic evaluation for short-term memory in visuomotor control, providing a standardized protocol to compare memory-augmented policies and guide development for long-horizon tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
