{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.18847", "kind": "paper", "url": "https://arxiv.org/abs/2606.18847"}], "authors": ["Yehang Zhang", "Jianchong Su", "Haojian Huang", "Yifan Chang", "Tianhao Zhou", "Xinli Xu", "Yingjie Xu", "Yinchuan Li", "Zexi Li", "Ying-Cong Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.18847", "source_url": "https://arxiv.org/abs/2606.18847"}, "categories": ["Robotics & Embodied AI", "cs.AI"], "description": {"en": "WorldLines evaluates long-horizon stateful embodied agents in household environments through Memory QA and Embodied Task Planning, using temporally extended household traces with dialogues and state changes."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.18847", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.18847", "title": "WorldLines"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.18847", "modality": null, "name": "WorldLines", "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_worldlines_ada0e776", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "931587d29492dcaad811be2eb8f5a9b1680c56934797ed629c83a8a8373523bb", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.18847"}, "publisher": null, "released": "2026-06-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.18847", "source_url": "https://arxiv.org/abs/2606.18847"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-18847", "source": "claire_radar", "source_benchmark_id": "2606.18847", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 6, "hfPaperUrl": "https://huggingface.co/papers/2606.18847", "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", "lastSuccessfulDate": "2026-10-02", "state": "stale"}}, "status": "stale"}, "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": "77c9ca12db8cf032d8beb481f9491e7bb0eedf978944ef78b14ad27ae2882300", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WorldLines evaluates long-horizon stateful embodied agents in household environments through Memory QA and Embodied Task Planning, using temporally extended household traces with dialogues and state changes.", "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"], "snippet": "We introduce WorldLines, a project-driven benchmark for long-horizon embodied household assistance."}, "familyId": "bmf_38b4fbd5fcdb", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_worldlines_ada0e776", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.18847", "paper": "https://arxiv.org/abs/2606.18847", "pdf": "https://arxiv.org/pdf/2606.18847", "project": null, "report": "https://arxiv.org/abs/2606.18847"}, "metrics": [], "motivation": "To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions.", "name": "WorldLines", "oneLine": "WorldLines evaluates long-horizon stateful embodied agents in household environments through Memory QA and Embodied Task Planning, using temporally extended household traces with dialogues and state changes.", "paperTitle": "WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": "Accepted to EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.18847", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.18847"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-17", "source": {"authors": ["Yehang Zhang", "Jianchong Su", "Haojian Huang", "Yifan Chang", "Tianhao Zhou", "Xinli Xu", "Yingjie Xu", "Yinchuan Li", "Zexi Li", "Ying-Cong Chen"], "categories": ["cs.AI"], "id": "2606.18847", "title": "WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.18847"}, "sourceUpdatedAt": "2026-06-17T09:26:26Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.18847"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026"}], "whyItMatters": "Existing benchmarks lack evaluation of long-term memory in dynamic embodied settings; WorldLines fills this gap by testing both memory retrieval and planning over extended interactions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
