{"record": {"aliases": ["TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases"], "artifacts": [{"id": "arxiv:2608.08727", "kind": "paper", "url": "https://arxiv.org/abs/2608.08727"}, {"id": "hf:enalis/tomammu", "kind": "dataset", "url": "https://huggingface.co/datasets/enalis/TomaMMU"}], "authors": ["Gia-Han Truong", "Khang Nguyen Quoc", "Luyl-Da Quach"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.08727", "source_url": "https://arxiv.org/abs/2608.08727"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "Evaluates vision-language models on tomato leaf disease understanding through seven tasks spanning basic perception, pathology understanding, and expert diagnosis using multimodal QA pairs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.08727", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.08727", "title": "TomaBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.08727", "modality": null, "name": "TomaBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_tomammu-a-comprehensive-multimodal-underst_69a4f816", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "3176acb6b7d7479a53e4e24b7429b907b5a929062764c980ee2a76888c01e5fa", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-03T09:03:47.731241Z", "source_url": "https://arxiv.org/abs/2608.08727"}, "publisher": null, "released": "2026-08-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.08727", "source_url": "https://arxiv.org/abs/2608.08727"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-08727", "source": "claire_radar", "source_benchmark_id": "2608.08727", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases"], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "enalis/TomaMMU", "hfDatasetDownloads": 34, "hfDatasetLikes": 1, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.08727", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a gap in domain-specific multimodal understanding and includes a large annotated dataset, which may attract attention from both agricultural AI and VLM communities.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T09:03:47.731241Z", "inputHash": "c0a6c42e86879532537f45160afede3c937522305771c8b8a7ed4f6ee7a8118e", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "alongside TomaBench, a benchmark for evaluating VLMs on tomato disease understanding", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is formally defined with a public dataset and code, and it proposes a clear evaluation protocol with three-level taxonomy; however, the data link is currently unverified.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T09:03:47.731241Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vision-language models on tomato leaf disease understanding through seven tasks spanning basic perception, pathology understanding, and expert diagnosis using multimodal QA pairs.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce TomaMMU, a large-scale Tomato leaf disease MultiModal Understanding dataset, alongside TomaBench, a benchmark for evaluating VLMs on tomato disease understanding."}, "familyId": "bmf_8680817893aa", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_tomammu-a-comprehensive-multimodal-underst_69a4f816", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": "https://huggingface.co/datasets/enalis/TomaMMU", "paper": "https://arxiv.org/abs/2608.08727", "pdf": "https://arxiv.org/pdf/2608.08727", "project": null, "report": "https://arxiv.org/abs/2608.08727"}, "metrics": [], "motivation": "To address this gap, we introduce TomaMMU, a large-scale Tomato leaf disease MultiModal Understanding dataset, alongside TomaBench, a benchmark for evaluating VLMs on tomato disease understanding.", "name": "TomaBench", "oneLine": "Evaluates vision-language models on tomato leaf disease understanding through seven tasks spanning basic perception, pathology understanding, and expert diagnosis using multimodal QA pairs.", "paperTitle": "TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": "Accepted at ECCV CVPPA Workshop", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.08727", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECCV CVPPA Workshop", "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.45, "datasetDownloadRank": 84, "datasetRankPopulation": 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": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.36612946919602324, "value": 34}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.45, "rank": 152, "score": 38}, "method": "attention-ranking-v13", "rank": 152, "score": 38}}, "readiness": "Inspectable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-08-09", "source": {"authors": ["Gia-Han Truong", "Khang Nguyen Quoc", "Luyl-Da Quach"], "categories": ["cs.CV", "cs.AI"], "id": "2608.08727", "title": "TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases", "type": "arxiv", "url": "https://arxiv.org/abs/2608.08727"}, "sourceUpdatedAt": "2026-08-09T14:20:49Z", "topics": ["Multimodal"], "venueAttempts": [{"decisionRaw": "Accepted at ECCV CVPPA Workshop", "evidence": [{"level": "author-claim", "observedAt": "2026-08-19T11:05:13.395391Z", "rawValue": "Accepted at ECCV CVPPA Workshop", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.08727"}], "reviewStatus": "accepted", "venueName": "ECCV CVPPA Workshop"}], "whyItMatters": "Introduces a large-scale, expert-structured benchmark to test fine-grained visual recognition and diagnostic reasoning in agricultural AI, enabling systematic model comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
