{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.01728", "kind": "paper", "url": "https://arxiv.org/abs/2607.01728"}], "authors": ["Licheng Zhang", "Bach Le", "Pengtao Zhao", "Naveed Akhtar"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.01728", "source_url": "https://arxiv.org/abs/2607.01728"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "WUICC-bench evaluates image change captioning for web UI visual regression testing, using natural language descriptions of UI changes. Scoring includes caption quality metrics and assesses suppression of non-meaningful noise."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.01728", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.01728", "title": "WUICC-bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The University of Melbourne"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.01728", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.01728", "source_url": "https://openalex.org/W7167266338"}, "key": "claire-radar:2607.01728", "modality": null, "name": "WUICC-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": "unknown", "origin_record_id": "bm_wuicc-bench_284cff3d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d7cac0791d89440ed756bf77bf3344b0946fea4264ce75846702be46e208d3ab", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.01728"}, "publisher": null, "released": "2026-07-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.01728", "source_url": "https://arxiv.org/abs/2607.01728"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-01728", "source": "claire_radar", "source_benchmark_id": "2607.01728", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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/2607.01728", "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": "73003b7c5003a2d8108102f09dfc900e16d0f36f07ed622e92a1e5532d2e96ec", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WUICC-bench evaluates image change captioning for web UI visual regression testing, using natural language descriptions of UI changes. Scoring includes caption quality metrics and assesses suppression of non-meaningful noise.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address the gap, we propose a new task, Web UI Image Change Captioning (WUICC), which sits at the intersection of VRT and image difference captioning (IDC), and release WUICC-bench, its first dataset and benchmark for the task."}, "familyId": "bmf_edbc54d76868", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_wuicc-bench_284cff3d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.01728", "paper": "https://arxiv.org/abs/2607.01728", "pdf": "https://arxiv.org/pdf/2607.01728", "project": null, "report": "https://arxiv.org/abs/2607.01728"}, "metrics": [], "motivation": "Visual regression testing (VRT) is a standard quality assurance step in modern software release pipelines.", "name": "WUICC-bench", "oneLine": "WUICC-bench evaluates image change captioning for web UI visual regression testing, using natural language descriptions of UI changes. Scoring includes caption quality metrics and assesses suppression of non-meaningful noise.", "paperTitle": "Beyond Pixel Diffs: Benchmarking Image Change Captioning for Web UI Visual Regression Testing", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.01728", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.01728"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-02", "source": {"authors": ["Licheng Zhang", "Bach Le", "Pengtao Zhao", "Naveed Akhtar"], "categories": ["cs.CV", "cs.CL", "cs.SE"], "id": "2607.01728", "title": "Beyond Pixel Diffs: Benchmarking Image Change Captioning for Web UI Visual Regression Testing", "type": "arxiv", "url": "https://arxiv.org/abs/2607.01728"}, "sourceUpdatedAt": "2026-07-02T05:33:57Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Pixel-level VRT is semantically blind and produces false positives. This benchmark enables development of change captioning systems that describe UI changes in words, improving regression testing efficiency."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
