{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.00154", "kind": "paper", "url": "https://arxiv.org/abs/2606.00154"}, {"id": "gh:anoa12159-hue/webigbench_eval", "kind": "repo", "url": "https://github.com/anoa12159-hue/WebIGBench_eval"}], "authors": ["Fan Wu", "Lishuai Dong", "Cuiyun Gao", "Yujia Chen", "Yiming Huang", "Yang Xiao", "Qing Liao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.00154", "source_url": "https://arxiv.org/abs/2606.00154"}, "categories": ["Code", "Code generation", "Multimodal", "Software & AI Compute"], "description": {"en": "WebIGBench evaluates code generation for interactive webpages with 103 complex examples and 871 distinct actions, proposing an automated evaluation pipeline for interactive consistency."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.00154", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.00154", "title": "WebIGBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Harbin Institute of Technology", "Chinese Academy of Sciences", "Institute of Information Engineering"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.00154", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.00154", "source_url": "https://openalex.org/W7163167486"}, "key": "claire-radar:2606.00154", "modality": null, "name": "WebIGBench", "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_webigbench_7eee6092", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "8ff995caf9ed0be89caaad54d968064c0eb0020e8d2db1c6958bc49edd4dff5a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.00154"}, "publisher": null, "released": "2026-05-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.00154", "source_url": "https://arxiv.org/abs/2606.00154"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-00154", "source": "claire_radar", "source_benchmark_id": "2606.00154", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/anoa12159-hue/WebIGBench_eval", "githubScope": "benchmark_repo", "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.00154", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Code generation"], "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": "02b84a3e54e2205d58f6e2672fdbbf08df43362a1a96f92846c3f9607760912d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WebIGBench evaluates code generation for interactive webpages with 103 complex examples and 871 distinct actions, proposing an automated evaluation pipeline for interactive consistency.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To address these limitations, we introduce WebIGBench, the first benchmark designed to evaluate code generation for interactive webpages with complex interactions."}, "familyId": "bmf_c2c33131ad91", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_webigbench_7eee6092", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/anoa12159-hue/WebIGBench_eval", "data": null, "hfPaper": "https://huggingface.co/papers/2606.00154", "paper": "https://arxiv.org/abs/2606.00154", "pdf": "https://arxiv.org/pdf/2606.00154", "project": null, "report": "https://arxiv.org/abs/2606.00154"}, "metrics": [], "motivation": "Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-end development.", "name": "WebIGBench", "oneLine": "WebIGBench evaluates code generation for interactive webpages with 103 complex examples and 871 distinct actions, proposing an automated evaluation pipeline for interactive consistency.", "paperTitle": "Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.00154", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-05-29", "source": {"authors": ["Fan Wu", "Lishuai Dong", "Cuiyun Gao", "Yujia Chen", "Yiming Huang", "Yang Xiao", "Qing Liao"], "categories": ["cs.SE", "cs.AI"], "id": "2606.00154", "title": "Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages", "type": "arxiv", "url": "https://arxiv.org/abs/2606.00154"}, "sourceUpdatedAt": "2026-05-29T05:45:50Z", "topics": ["Multimodal", "Code"], "venueAttempts": [], "whyItMatters": "Fills the gap in benchmarking interactive webpage code generation, offering a public dataset and evaluation method for model comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
