{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.04598", "kind": "paper", "url": "https://arxiv.org/abs/2609.04598"}], "authors": ["Taegyun Kim", "Youngwook Ham", "Jungwook Rhim", "Ju-Hyun An", "Sungkyu Park", "Kunwoo Park"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.04598", "source_url": "https://arxiv.org/abs/2609.04598"}, "categories": ["Biology & Drug Discovery", "Factuality", "Multimodal", "Reasoning"], "description": {"en": "Evaluates large language and vision-language models on Korean veterinary question answering, covering text and multimodal questions with expert answers and multiple evaluation metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.04598", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.04598", "title": "PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.04598", "modality": null, "name": "PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "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_petqa-benchmarking-veterinary-knowledge-an_ed0d2f9f", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "f0dc8a15824b6e8c216274bf069d5d1bbc7d50783fd08b197bacc068bdf6f214", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-10T09:02:48.332472Z", "source_url": "https://arxiv.org/abs/2609.04598"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.04598", "source_url": "https://arxiv.org/abs/2609.04598"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-04598", "source": "claire_radar", "source_benchmark_id": "2609.04598", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "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": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.04598", "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"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a niche veterinary domain with a large dataset and multi-model evaluation, which may attract moderate attention from researchers working on domain-specific QA and medical AI.", "score": 55}, "capabilities": ["Reasoning", "Factuality"], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-10T09:02:48.332472Z", "inputHash": "e1cbaef3fd6cc4c4c113ce94898038f517819305e9d98fa2b6431724246d2544", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark includes a released test split with defined evaluation metrics and is intended for broader use, including multilingual translations.", "evaluationEvidence": {"reuse": "The test split, PetQA-Bench, is released with annotations, and translated versions in five languages are provided to facilitate broader use.", "scoring": "Metrics include ROUGE, BERTScore, and LLM-as-a-judge for factuality and helpfulness under three settings: zero-shot inference, retrieval-augmented generation (RAG), and supervised fine-tuning (SFT).", "task": "PetQA is a Korean long-form question-answering benchmark containing 10,076 text-only and 8,751 multimodal QA pairs derived from real-world questions about dogs and cats, paired with answers from expert veterinarians."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-10T09:02:48.332472Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates large language and vision-language models on Korean veterinary question answering, covering text and multimodal questions with expert answers and multiple evaluation metrics.", "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"], "snippet": "We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language models (LLMs) and large vision-language models (LVLMs)."}, "familyId": "bmf_19d0845170a2", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_petqa-benchmarking-veterinary-knowledge-an_ed0d2f9f", "indexedAt": "2026-09-07T06:22:02.605340Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.04598", "pdf": "https://arxiv.org/pdf/2609.04598", "project": null, "report": "https://arxiv.org/abs/2609.04598"}, "metrics": [], "motivation": "We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language models (LLMs) and large vision-language models (LVLMs).", "name": "PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning", "oneLine": "Evaluates large language and vision-language models on Korean veterinary question answering, covering text and multimodal questions with expert answers and multiple evaluation metrics.", "paperTitle": "PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.04598", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T06:22:02.605340Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-09-04", "source": {"authors": ["Taegyun Kim", "Youngwook Ham", "Jungwook Rhim", "Ju-Hyun An", "Sungkyu Park", "Kunwoo Park"], "categories": ["cs.CL", "cs.AI", "cs.CV"], "id": "2609.04598", "title": "PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2609.04598"}, "sourceUpdatedAt": "2026-09-04T00:54:04Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "Provides a large-scale, clinically grounded resource for assessing veterinary knowledge and reasoning, enabling comparison across model settings and identifying gaps for reliable veterinary AI."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
