{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.03499", "kind": "paper", "url": "https://arxiv.org/abs/2608.03499"}, {"id": "gh:kingofspace0wzz/weclawarena", "kind": "repo", "url": "https://github.com/kingofspace0wzz/WeClawArena"}], "authors": ["Prince Zizhuang Wang", "Aojie Yuan", "Haiyue Zhang", "Xiyang Hu", "Yue Zhao", "Shuli Jiang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.03499", "source_url": "https://arxiv.org/abs/2608.03499"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "WeClawArena is a benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. It contains 124 base tasks across six domains, expanded into 620 scenario variants with benign and attack-vector conditions, and reports task success and attack success separately."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.03499", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.03499", "title": "WeClawArena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.03499", "modality": null, "name": "WeClawArena", "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_weclawarena_f743496b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a93c8238770a26c3876de8412b91508e9c23cc631e98631d8b633a936f440b27", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.03499"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.03499", "source_url": "https://arxiv.org/abs/2608.03499"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-03499", "source": "claire_radar", "source_benchmark_id": "2608.03499", "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": "https://github.com/kingofspace0wzz/WeClawArena", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": "2026-08-11T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 8, "hfPaperUrl": "https://huggingface.co/papers/2608.03499", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "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": "2a0bad212dc0d7814ba1d3019a723e8879bca65b589da7017ae5b891d1371589", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WeClawArena is a benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. It contains 124 base tasks across six domains, expanded into 620 scenario variants with benign and attack-vector conditions, and reports task success and attack success separately.", "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 WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces."}, "familyId": "bmf_4cf9742a8ee1", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/kingofspace0wzz/WeClawArena", "url": "https://github.com/kingofspace0wzz/WeClawArena"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/kingofspace0wzz/WeClawArena", "url": "https://huggingface.co/papers/2608.03499"}], "scope": "benchmark_repo", "url": "https://github.com/kingofspace0wzz/WeClawArena", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_weclawarena_f743496b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/kingofspace0wzz/WeClawArena", "data": null, "hfPaper": "https://huggingface.co/papers/2608.03499", "paper": "https://arxiv.org/abs/2608.03499", "pdf": "https://arxiv.org/pdf/2608.03499", "project": null, "report": "https://arxiv.org/abs/2608.03499"}, "metrics": [], "motivation": "Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations.", "name": "WeClawArena", "oneLine": "WeClawArena is a benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. It contains 124 base tasks across six domains, expanded into 620 scenario variants with benign and attack-vector conditions, and reports task success and attack success separately.", "paperTitle": "WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.03499", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "kingofspace0wzz", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/kingofspace0wzz/WeClawArena"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.3882377386428991, "value": 8}}, "confidence": "Medium", "coverage": 0.7, "rank": 362, "score": 26}, "method": "attention-ranking-v13", "rank": 362, "score": 26}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-04", "source": {"authors": ["Prince Zizhuang Wang", "Aojie Yuan", "Haiyue Zhang", "Xiyang Hu", "Yue Zhao", "Shuli Jiang"], "categories": ["cs.AI"], "id": "2608.03499", "title": "WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks", "type": "arxiv", "url": "https://arxiv.org/abs/2608.03499"}, "sourceUpdatedAt": "2026-08-04T11:42:26Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Existing agent benchmarks do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic digital workspaces. WeClawArena enables evaluation of both collaborative task utility and security risks in human-centered agent networks, supporting diagnosis of privacy leakage, poisoned evidence, and invalid authority paths."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
