{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04830", "kind": "paper", "url": "https://arxiv.org/abs/2608.04830"}], "authors": ["Bo Wang", "Yuqian Yao", "Enxi Wang", "Luozhijie Jin", "Yang Liu", "Yiran Suo", "Yuxuan Cai", "Enyu Zhou", "Yufei Gao", "Honglin Guo", "Tianyu Huai", "Li Ji", "Zhikai Lei", "Bufan Li", "Lizhi Lin", "Jinxiu Liu", "Jie Yang", "Jiazheng Zhou", "Maosen Zhou", "Pengfang Qian", "Shichun Liu", "Guanshan Liu", "Hao Zheng", "Yunhao Yu", "Hang Yan", "Jihua Kang", "Xinchi Chen", "Xipeng Qiu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04830", "source_url": "https://arxiv.org/abs/2608.04830"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "ContextWeave is a longitudinal benchmark for evaluating memory in office workflows, with 1,005 executable tasks from 14 participants. It measures workspace quality and preference alignment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04830", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04830", "title": "ContextWeave"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Fudan University", "Shanghai Innovation Institute", "ByteDance (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.04830", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.04830", "source_url": "https://openalex.org/W7197021468"}, "key": "claire-radar:2608.04830", "modality": null, "name": "ContextWeave", "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_contextweave_c388d0b9", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ebd1f68e748099747e33a95489cee68240c754b7998aefe0a20b4e2c77e5577f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.04830"}, "publisher": null, "released": "2026-08-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04830", "source_url": "https://arxiv.org/abs/2608.04830"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04830", "source": "claire_radar", "source_benchmark_id": "2608.04830", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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/2608.04830", "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"}, "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": "696b147cae0380d7a7acd8296bd7539985e234930bdd8b98236ea664f191fc21", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ContextWeave is a longitudinal benchmark for evaluating memory in office workflows, with 1,005 executable tasks from 14 participants. It measures workspace quality and preference alignment.", "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 ContextWeave, a longitudinal benchmark that evaluates whether recalled experience improves downstream agent performance in realistic office-work streams."}, "familyId": "bmf_a571d6806b2e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_contextweave_c388d0b9", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.04830", "paper": "https://arxiv.org/abs/2608.04830", "pdf": "https://arxiv.org/pdf/2608.04830", "project": null, "report": "https://arxiv.org/abs/2608.04830"}, "metrics": [], "motivation": "Memory is essential as language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to retrieval or question answering.", "name": "ContextWeave", "oneLine": "ContextWeave is a longitudinal benchmark for evaluating memory in office workflows, with 1,005 executable tasks from 14 participants. It measures workspace quality and preference alignment.", "paperTitle": "ContextWeave: A Real-World Workflow Benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04830", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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": 1.0, "relation": "introduces", "releasedAt": "2026-08-05", "source": {"authors": ["Bo Wang", "Yuqian Yao", "Enxi Wang", "Luozhijie Jin", "Yang Liu", "Yiran Suo", "Yuxuan Cai", "Enyu Zhou", "Yufei Gao", "Honglin Guo", "Tianyu Huai", "Li Ji", "Zhikai Lei", "Bufan Li", "Lizhi Lin", "Jinxiu Liu", "Jie Yang", "Jiazheng Zhou", "Maosen Zhou", "Pengfang Qian", "Shichun Liu", "Guanshan Liu", "Hao Zheng", "Yunhao Yu", "Hang Yan", "Jihua Kang", "Xinchi Chen", "and Xipeng Qiu"], "categories": ["cs.AI"], "id": "2608.04830", "title": "ContextWeave: A Real-World Workflow Benchmark", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04830"}, "sourceUpdatedAt": "2026-08-05T13:31:18Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "It addresses evaluation of memory in long-horizon agent workflows, but the lack of public artifacts and scoring details makes it non-reusable without further information."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
