{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.00048", "kind": "paper", "url": "https://arxiv.org/abs/2609.00048"}], "authors": ["Lin Fu", "Zheyuan Yang", "Tianhui Zhang", "Jinbiao Wei", "Guo Gan", "Boxu Liu", "Yilun Zhao", "Yu Rong"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.00048", "source_url": "https://arxiv.org/abs/2609.00048"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "GUI-CC evaluates whether GUI world models maintain contextual consistency in multi-step agent interactions using offline reference trajectories and online probing agents."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.00048", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.00048", "title": "GUI-CC"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.00048", "modality": null, "name": "GUI-CC", "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": "true", "origin_record_id": "bm_gui-cc_ad8b1116", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5482ca0e33d3470a7cda7d64bd4023025f09a28b99be043046f376144ead7a3a", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2609.00048"}, "publisher": null, "released": "2026-08-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.00048", "source_url": "https://arxiv.org/abs/2609.00048"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-00048", "source": "claire_radar", "source_benchmark_id": "2609.00048", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": "https://github.com/Fu-Fu-Fu-Fu/GUI-CC", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": "2026-09-01T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 8, "hfPaperUrl": "https://huggingface.co/papers/2609.00048", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "GUI agent evaluation is a trending area, but the forecast is limited by the absence of public artifacts.", "score": 70}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "ebbb858ddeaa9fe8a205601fa408a4d43a2160016a7f6fedf888394f272f9afb", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce GUI-CC, a benchmark that evaluates contextual consistency of GUI world models as agent environments rather than isolated next-screen predictors.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark defines clear evaluation tracks and reports quantitative results, though no public code or data link is provided in the abstract.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GUI-CC evaluates whether GUI world models maintain contextual consistency in multi-step agent interactions using offline reference trajectories and online probing agents.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce GUI-CC, a benchmark that evaluates contextual consistency of GUI world models as agent environments rather than isolated next-screen predictors."}, "familyId": "bmf_2c7fc47d350a", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_gui-cc_ad8b1116", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.00048", "pdf": "https://arxiv.org/pdf/2609.00048", "project": null, "report": "https://arxiv.org/abs/2609.00048"}, "metrics": [], "motivation": "GUI world models are increasingly evaluated as one-step next-screen predictors, yet their intended use is often as multi-step environments for GUI agents.", "name": "GUI-CC", "oneLine": "GUI-CC evaluates whether GUI world models maintain contextual consistency in multi-step agent interactions using offline reference trajectories and online probing agents.", "paperTitle": "GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.00048", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "ranking": {"30d": {"confidence": "High", "coverage": 0.85, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.10323645750017778, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.3894471407822876, "value": 8}}, "confidence": "High", "coverage": 0.85, "rank": 112, "score": 25}, "method": "attention-ranking-v13", "rank": 112, "score": 25}, "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": 0.09434039834931938, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.3894471407822876, "value": 8}}, "confidence": "Medium", "coverage": 0.7, "rank": 295, "score": 26}, "method": "attention-ranking-v13", "rank": 295, "score": 26}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-30", "source": {"authors": ["Lin Fu", "Zheyuan Yang", "Tianhui Zhang", "Jinbiao Wei", "Guo Gan", "Boxu Liu", "Yilun Zhao", "Yu Rong"], "categories": ["cs.CL", "cs.AI"], "id": "2609.00048", "title": "GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments", "type": "arxiv", "url": "https://arxiv.org/abs/2609.00048"}, "sourceUpdatedAt": "2026-08-30T05:19:43Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "It reveals a critical gap between single-step screen prediction and reliable multi-step environment simulation for GUI agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
