{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.14383", "kind": "paper", "url": "https://arxiv.org/abs/2606.14383"}, {"id": "gh:alibaba-multimodal-industrial-ai/industrybench-mipu", "kind": "repo", "url": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU"}], "authors": ["Haonan Qi", "Jin Cao", "Yongqi Zhang", "Xintong Wang", "Weidong Tang", "Bin Chen", "Chengfu Huo", "Haojun Pan", "Hengyu You", "Jing Li", "Yingde Wang", "Liang Ding"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.14383", "source_url": "https://arxiv.org/abs/2606.14383"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "IndustryBench-MIPU evaluates MLLMs on extracting structured attribute-value pairs from multi-image industrial product data, covering text recognition, visual reasoning, and cross-image integration."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.14383", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.14383", "title": "IndustryBench-MIPU"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.14383", "modality": null, "name": "IndustryBench-MIPU", "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_industrybench-mipu_6704f5ae", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2334d2f477eb72f794c74ac121410752fd3244df22ce7be8fa3a18ca4eacc26a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.14383"}, "publisher": null, "released": "2026-06-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.14383", "source_url": "https://arxiv.org/abs/2606.14383"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-14383", "source": "claire_radar", "source_benchmark_id": "2606.14383", "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": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU", "githubScope": "benchmark_repo", "githubStars": 12, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 4, "hfPaperUrl": "https://huggingface.co/papers/2606.14383", "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", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "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": "f62a1ce1637e2cb638f2f123a1f25a2591353c98cd163fea25419178a97024a7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "IndustryBench-MIPU evaluates MLLMs on extracting structured attribute-value pairs from multi-image industrial product data, covering text recognition, visual reasoning, and cross-image integration.", "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 fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction -- recovering property-value pairs from product images."}, "familyId": "bmf_6260f7570604", "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/alibaba-multimodal-industrial-ai/IndustryBench-MIPU", "url": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU", "url": "https://huggingface.co/papers/2606.14383"}], "scope": "benchmark_repo", "url": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_industrybench-mipu_6704f5ae", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU", "data": null, "hfPaper": "https://huggingface.co/papers/2606.14383", "paper": "https://arxiv.org/abs/2606.14383", "pdf": "https://arxiv.org/pdf/2606.14383", "project": null, "report": "https://arxiv.org/abs/2606.14383"}, "metrics": [], "motivation": "Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains.", "name": "IndustryBench-MIPU", "oneLine": "IndustryBench-MIPU evaluates MLLMs on extracting structured attribute-value pairs from multi-image industrial product data, covering text recognition, visual reasoning, and cross-image integration.", "paperTitle": "IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.14383", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Alibaba", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/alibaba-multimodal-industrial-ai/IndustryBench-MIPU"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-12", "source": {"authors": ["Haonan Qi", "Jin Cao", "Yongqi Zhang", "Xintong Wang", "Weidong Tang", "Bin Chen", "Chengfu Huo", "Haojun Pan", "Hengyu You", "Jing Li", "Yingde Wang", "Liang Ding"], "categories": ["cs.CV"], "id": "2606.14383", "title": "IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products", "type": "arxiv", "url": "https://arxiv.org/abs/2606.14383"}, "sourceUpdatedAt": "2026-06-16T03:59:08Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Industrial product specifications are scattered across images, and current MLLMs show a recall gap; this benchmark quantifies multi-image understanding limits for procurement and safety."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
