{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.29532", "kind": "paper", "url": "https://arxiv.org/abs/2605.29532"}], "authors": ["Xiaoyi Chen", "Yifei Gao", "Yang Xu", "Zhenlong Wang", "Jian Yan", "Jiming An", "Xingxing Song", "Liqun Deng", "Xiaojun Meng", "Jiansheng Wei", "Yi Zhang", "Jitao Sang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.29532", "source_url": "https://arxiv.org/abs/2605.29532"}, "categories": ["Agents", "Agents & Tool Use", "Mobile & Personal Computing"], "description": {"en": "Evaluates exploratory GUI testing agents on 61 Android apps with 508 preset defects, using an open-set evaluator that decomposes trajectories into independently diagnosable capabilities."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.29532", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.29532", "title": "GUITestScape"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.29532", "modality": null, "name": "GUITestScape", "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_guitestscape_3504136d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "49158d55ea2c06dd58ab4c0235bddbfb0bc01ead3d69fa9b9156f4fa399f1f2a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.29532"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.29532", "source_url": "https://arxiv.org/abs/2605.29532"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-29532", "source": "claire_radar", "source_benchmark_id": "2605.29532", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Mobile & Personal Computing"], "area": "Agents & Tool Use", "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/2605.29532", "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": "2026-08-21T04:30:40.934319Z", "inputHash": "ab255589bec9fea07fcf9736827fa3dcdddd5ccf8418b8d43d4dc5fb156e186e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates exploratory GUI testing agents on 61 Android apps with 508 preset defects, using an open-set evaluator that decomposes trajectories into independently diagnosable capabilities.", "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": "To address these challenges, we present GUITestScape, an interactive benchmark covering 61 real-world Android applications and 508 preset defects spanning interaction and display types, and introduce GUIJudge, an open-set evaluator that decomposes an agent's testing trajectory into independently diagnosable capabilities."}, "familyId": "bmf_ceab67585453", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_guitestscape_3504136d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Consumer Technology"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.29532", "paper": "https://arxiv.org/abs/2605.29532", "pdf": "https://arxiv.org/pdf/2605.29532", "project": null, "report": "https://arxiv.org/abs/2605.29532"}, "metrics": [], "motivation": "Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application and discover defects through its own interaction.", "name": "GUITestScape", "oneLine": "Evaluates exploratory GUI testing agents on 61 Android apps with 508 preset defects, using an open-set evaluator that decomposes trajectories into independently diagnosable capabilities.", "paperTitle": "GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing", "primaryDomain": "Mobile & Personal Computing", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.29532", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "GUITestScape Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2605.29532"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Xiaoyi Chen", "Yifei Gao", "Yang Xu", "Xingxing Song", "Yi Zhang", "Jitao Sang"], "categories": ["cs.SE", "cs.AI"], "id": "2605.29532", "title": "GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing", "type": "arxiv", "url": "https://arxiv.org/abs/2605.29532"}, "sourceUpdatedAt": "2026-05-28T07:47:27Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Addresses the lack of open-set evaluation in GUI testing, covering interaction and display defects. Provides a finer-grained assessment of agent capabilities and a verifier integration boost."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
