{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.22338", "kind": "paper", "url": "https://arxiv.org/abs/2606.22338"}, {"kind": "repo", "url": "https://github.com/SoumilRathi/robomme-interference/blob/main/results/analysis/tables/main_success_rates.csv"}, {"kind": "website", "url": "https://robotmemorybench.com"}], "authors": ["Soumil Rathi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.22338", "source_url": "https://arxiv.org/abs/2606.22338"}, "categories": ["Robotics", "Robotics & Embodied AI"], "description": {"en": "RoboMME-Interference evaluates robot long-context memory under cross-session interference. The benchmark builds on RoboMME, constructing session histories per query episode with relevant demonstration plus controlled unrelated sessions, and measures task success for memory-augmented vision-language-action models."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.22338", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.22338", "title": "RoboMME-Interference"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.22338", "modality": null, "name": "RoboMME-Interference", "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_robomme-interference_7b518e1a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "890fedde63764f33df1718c037a30e160656206a038243b5f28947055bbae3ac", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.22338"}, "publisher": null, "released": "2026-06-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.22338", "source_url": "https://arxiv.org/abs/2606.22338"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-22338", "source": "claire_radar", "source_benchmark_id": "2606.22338", "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/SoumilRathi/robomme-interference", "githubScope": "hosting_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.22338", "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", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b9d6394cb1ee7992ed3105c080ada8703802ee95f9e1baebb3eaabc55a46ca8e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RoboMME-Interference evaluates robot long-context memory under cross-session interference. The benchmark builds on RoboMME, constructing session histories per query episode with relevant demonstration plus controlled unrelated sessions, and measures task success for memory-augmented vision-language-action models.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To measure how current robot memory systems perform on longer sessions with more distractions, we introduce RoboMME-Interference, a cross-session benchmark built on RoboMME."}, "familyId": "bmf_f0a1facb41ae", "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/SoumilRathi/robomme-interference/blob/main/results/analysis/tables/main_success_rates.csv", "url": "https://robotmemorybench.com"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/SoumilRathi/robomme-interference/blob/main/results/canonical_rollouts.csv", "url": "https://robotmemorybench.com"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/SoumilRathi/robomme-interference/tree/main/results", "url": "https://robotmemorybench.com"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/SoumilRathi/robomme-interference", "url": "https://robotmemorybench.com"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/SoumilRathi/robomme-interference/blob/main/README.md", "url": "https://robotmemorybench.com"}], "scope": "benchmark_repo", "url": "https://github.com/SoumilRathi/robomme-interference", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_robomme-interference_7b518e1a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/SoumilRathi/robomme-interference/blob/main/results/analysis/tables/main_success_rates.csv", "data": null, "hfPaper": "https://huggingface.co/papers/2606.22338", "paper": "https://arxiv.org/abs/2606.22338", "pdf": "https://arxiv.org/pdf/2606.22338", "project": "https://robotmemorybench.com", "report": "https://arxiv.org/abs/2606.22338"}, "metrics": [], "motivation": "Robots deployed in realistic settings will accumulate experience across many sessions and tasks over their deployment.", "name": "RoboMME-Interference", "oneLine": "RoboMME-Interference evaluates robot long-context memory under cross-session interference. The benchmark builds on RoboMME, constructing session histories per query episode with relevant demonstration plus controlled unrelated sessions, and measures task success for memory-augmented vision-language-action models.", "paperTitle": "RoboMME-Interference: Benchmarking Robot Memory Under Interference", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.22338", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "robotmemorybench.com", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://robotmemorybench.com"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-21", "source": {"authors": ["Soumil Rathi"], "categories": ["cs.RO", "cs.AI", "cs.LG"], "id": "2606.22338", "title": "RoboMME-Interference: Benchmarking Robot Memory Under Interference", "type": "arxiv", "url": "https://arxiv.org/abs/2606.22338"}, "sourceUpdatedAt": "2026-07-28T00:23:57Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Existing robot memory benchmarks ignore realistic multi-session interference. RoboMME-Interference quantifies how memory decays with unrelated sessions and whether retrieval mechanisms restore robustness, providing practical decision value for long-deployed robots."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
