{"record": {"aliases": ["Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery"], "artifacts": [{"id": "arxiv:2608.06931", "kind": "paper", "url": "https://arxiv.org/abs/2608.06931"}], "authors": ["Taolin Han", "Yuchen Zhang", "Jinghang Wang", "Yun Wu", "Wai Yuet Chiu", "Zhaohai Li", "Yifei Zhang", "Jinxin Wang", "Yuhao Zhou", "Chen Zhao", "Jiajia Li", "Jiaxin Li", "Qile Jin", "Kewei Sun", "Shuang Wu", "Weiqi Zhai", "Renquan Lv", "Junchao Li", "Ruodan Chen", "Qingteng Chen", "Zhibo Yang", "Hu Wei", "Lin Qu", "Shuai Bai", "Bing Zhao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.06931", "source_url": "https://arxiv.org/abs/2608.06931"}, "categories": ["AI Scientist", "Materials & Chemistry", "Multimodal"], "description": {"en": "Science Edge Evaluation (SEE) is a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science, evaluated via accuracy across MLLMs and tool-use agents."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.06931", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.06931", "title": "Science Edge Evaluation"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Alberta", "Alibaba Group (China)", "Tsinghua University", "Alibaba Group (United States)", "Zhejiang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.06931", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.06931", "source_url": "https://openalex.org/W7202113316"}, "key": "claire-radar:2608.06931", "modality": null, "name": "Science Edge Evaluation", "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_science-edge-evaluation-see-the-missing-st_165cace2", "origin_source": "arxiv", "recognition_confidence": "0.45", "record_sha256": "983e2af2798957254c19a4e750933904aa33ea53710bc09b3261841e3db7fe38", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-04T08:56:32.129656Z", "source_url": "https://arxiv.org/abs/2608.06931"}, "publisher": null, "released": "2026-08-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.06931", "source_url": "https://arxiv.org/abs/2608.06931"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-06931", "source": "claire_radar", "source_benchmark_id": "2608.06931", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery"], "annotation": "Unknown", "applicationDomains": ["Materials & Chemistry"], "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/2608.06931", "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 targets the timely topic of LLM scientific reasoning and reports evaluations across 19 MLLMs, likely to generate immediate community interest.", "score": 60}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-04T08:56:32.129656Z", "inputHash": "0bf41fe38fa1e3b21d228bd554f3e445ad5505f15e7293c0933f4d2b74c0d484", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "Here we introduce Science Edge Evaluation (SEE), a multimodal benchmark", "canonicalNameSource": "abstract", "decisionReason": "The paper clearly defines the benchmark with a fixed set of questions and scoring accuracy, and the publication supports a public reuse path as a released evaluation suite.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T08:56:32.129656Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Science Edge Evaluation (SEE) is a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science, evaluated via accuracy across MLLMs and tool-use agents.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence"], "snippet": "Here we introduce Science Edge Evaluation (SEE), a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science."}, "familyId": "bmf_6546f9012d85", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_science-edge-evaluation-see-the-missing-st_165cace2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Materials & Chemicals"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.06931", "pdf": "https://arxiv.org/pdf/2608.06931", "project": null, "report": "https://arxiv.org/abs/2608.06931"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science.", "name": "Science Edge Evaluation", "oneLine": "Science Edge Evaluation (SEE) is a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science, evaluated via accuracy across MLLMs and tool-use agents.", "paperTitle": "Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery", "primaryDomain": "Materials & Chemistry", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.06931", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "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": 0.45, "relation": "introduces", "releasedAt": "2026-08-07", "source": {"authors": ["Taolin Han", "Yuchen Zhang", "Jinghang Wang", "Yun Wu", "Wai Yuet Chiu", "Zhaohai Li", "Yifei Zhang", "Jinxin Wang", "Yuhao Zhou", "Chen Zhao", "Jiajia Li", "Jiaxin Li", "Qile Jin", "Kewei Sun", "Shuang Wu", "Weiqi Zhai", "Renquan Lv", "Junchao Li", "Ruodan Chen", "Qingteng Chen", "Zhibo Yang", "Hu Wei", "Lin Qu", "Shuai Bai", "and Bing Zhao"], "categories": ["cs.AI"], "id": "2608.06931", "title": "Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery", "type": "arxiv", "url": "https://arxiv.org/abs/2608.06931"}, "sourceUpdatedAt": "2026-08-07T08:06:31Z", "topics": ["AI Scientist", "Multimodal"], "venueAttempts": [], "whyItMatters": "It provides a rigorous testbed for assessing evidence-bounded scientific reasoning in multimodal LLMs, highlighting current limitations in real scientific discovery tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
