{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.07712", "kind": "paper", "url": "https://arxiv.org/abs/2609.07712"}, {"id": "gh:acrab-agentic-labs/appsim", "kind": "repo", "url": "https://github.com/Acrab-Agentic-Labs/AppSim"}], "authors": ["Jintian Feng", "Long Chen", "Xiao Yu", "Jiayi Dai", "Chenglong Liu", "Haoru Wang", "Zizhen Xue", "Yuxuan Shi", "Ziyang Wang", "Yichen Gong"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.07712", "source_url": "https://arxiv.org/abs/2609.07712"}, "categories": ["Agents & Tool Use", "General AI", "cs.AI"], "description": {"en": "Controllable simulated apps for mobile GUI agent evaluation, containing 557 tasks across 17 Chinese and English apps with deterministic backend data and outcome-based verification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.07712", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.07712", "title": "AppSim-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.07712", "modality": null, "name": "AppSim-Bench", "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": "false", "origin_record_id": "bm_appsim-bench_0821b282", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "29024343f86e7b8aed1030e539996dfa6a6acdd6ff101235d256811867215cfc", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-09T06:27:57.312318Z", "source_url": "https://arxiv.org/abs/2609.07712"}, "publisher": null, "released": "2026-09-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.07712", "source_url": "https://arxiv.org/abs/2609.07712"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-07712", "source": "claire_radar", "source_benchmark_id": "2609.07712", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Acrab-Agentic-Labs/AppSim", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.07712", "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", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Mobile agent evaluation is an active area and the preprint includes a project URL, but artifact availability is uncertain.", "score": 51}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T06:27:57.312318Z", "inputHash": "674ba25d2146044f9a8c6361a215bc8b2d8fa012facd4fcf5954cc18ec948249", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Code link is unverified and no analysis artifact excerpt confirms the benchmark data or evaluation protocol is publicly accessible.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Controllable simulated apps for mobile GUI agent evaluation, containing 557 tasks across 17 Chinese and English apps with deterministic backend data and outcome-based verification.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We propose AppSim-Bench, which addresses this trade-off through controllable simulated apps that preserve task-relevant interaction logic while supporting deterministic evaluation."}, "familyId": "bmf_6c9b3243254c", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_appsim-bench_0821b282", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": [], "links": {"code": "https://github.com/Acrab-Agentic-Labs/AppSim", "data": null, "paper": "https://arxiv.org/abs/2609.07712", "pdf": "https://arxiv.org/pdf/2609.07712", "project": null, "report": "https://arxiv.org/abs/2609.07712"}, "metrics": [], "motivation": "Mobile GUI agents can execute tasks from natural-language instructions, but their evaluation remains difficult to make both realistic and reproducible.", "name": "AppSim-Bench", "oneLine": "Controllable simulated apps for mobile GUI agent evaluation, containing 557 tasks across 17 Chinese and English apps with deterministic backend data and outcome-based verification.", "paperTitle": "APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.07712", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.16198483906027114, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 79, "score": 31}, "method": "attention-ranking-v13", "rank": 79, "score": 31}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 252, "score": 31}, "method": "attention-ranking-v13", "rank": 252, "score": 31}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-07", "source": {"authors": ["Jintian Feng", "Long Chen", "Xiao Yu", "Jiayi Dai", "Chenglong Liu", "Haoru Wang", "Zizhen Xue", "Yuxuan Shi", "Ziyang Wang", "Yichen Gong"], "categories": ["cs.AI"], "id": "2609.07712", "title": "APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2609.07712"}, "sourceUpdatedAt": "2026-09-07T16:25:13Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Aims to provide realistic yet reproducible mobile agent evaluation by avoiding stochastic commercial app environments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
