{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.06306", "kind": "paper", "url": "https://arxiv.org/abs/2607.06306"}, {"id": "gh:chenmancm169/ui2app", "kind": "repo", "url": "https://github.com/chenmancm169/UI2App"}], "authors": ["Grace Man Chen", "Litao Guo", "Yifan Wu", "Yiyu Chen", "Yenchi Tseng", "Sicheng Liu", "Yuyu Luo", "Ying-Cong Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.06306", "source_url": "https://arxiv.org/abs/2607.06306"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "Benchmarks visual interaction inference in executable web application generation. Contains 327 screenshots in 45 sets, evaluating executability, navigation reachability, visual fidelity, and interaction inference via the IIS metric."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.06306", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.06306", "title": "UI2App"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.06306", "modality": null, "name": "UI2App", "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_ui2app_cf415439", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "19dac00b873562dd394c3669dbadf968915c07ec0152bf88452736a5fb038317", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.06306"}, "publisher": null, "released": "2026-07-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.06306", "source_url": "https://arxiv.org/abs/2607.06306"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-06306", "source": "claire_radar", "source_benchmark_id": "2607.06306", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/chenmancm169/UI2App", "githubScope": "benchmark_repo", "githubStars": 4, "hfDailySubmittedAt": "2026-07-21T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 3, "hfPaperUrl": "https://huggingface.co/papers/2607.06306", "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": "1ddac74dcec827323df25757304b635430681d503488d8ea5f382cda06cfa635", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Benchmarks visual interaction inference in executable web application generation. Contains 327 screenshots in 45 sets, evaluating executability, navigation reachability, visual fidelity, and interaction inference via the IIS metric.", "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 this gap, we introduce UI2App, the first benchmark targeting interaction inference, the ability to recover application behavior from screenshots alone, without any textual or behavioral guidance."}, "familyId": "bmf_aca78e2fdb0c", "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/chenmancm169/UI2App", "url": "https://github.com/chenmancm169/UI2App"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/chenmancm169/UI2App", "url": "https://huggingface.co/papers/2607.06306"}], "scope": "benchmark_repo", "url": "https://github.com/chenmancm169/UI2App", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ui2app_cf415439", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/chenmancm169/UI2App", "data": null, "hfPaper": "https://huggingface.co/papers/2607.06306", "paper": "https://arxiv.org/abs/2607.06306", "pdf": "https://arxiv.org/pdf/2607.06306", "project": null, "report": "https://arxiv.org/abs/2607.06306"}, "metrics": [], "motivation": "Large language models (LLMs) have demonstrated growing competence in web page generation.", "name": "UI2App", "oneLine": "Benchmarks visual interaction inference in executable web application generation. Contains 327 screenshots in 45 sets, evaluating executability, navigation reachability, visual fidelity, and interaction inference via the IIS metric.", "paperTitle": "UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.06306", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": 0.21483102985913266, "value": 4}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.24495074076910422, "value": 3}}, "confidence": "Medium", "coverage": 0.7, "rank": 273, "score": 30}, "method": "attention-ranking-v13", "rank": 273, "score": 30}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-07", "source": {"authors": ["Grace Man Chen", "Litao Guo", "Yifan Wu", "Yiyu Chen", "Yenchi Tseng", "Sicheng Liu", "Yuyu Luo", "Ying-Cong Chen"], "categories": ["cs.SE", "cs.AI", "cs.CV"], "id": "2607.06306", "title": "UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.06306"}, "sourceUpdatedAt": "2026-07-07T14:08:55Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Targets a gap in measuring behavior inference from screenshots, not just visual fidelity. Could help assess models' ability to produce interactive applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
