{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25398", "kind": "paper", "url": "https://arxiv.org/abs/2608.25398"}, {"id": "gh:ecnu-rail/omniphys-emnlp2026", "kind": "repo", "url": "https://github.com/ECNU-RAIL/OmniPhys-EMNLP2026"}], "authors": ["Hao Chen", "Yumin Lin", "Nadila Yushanjiang", "Xin Lin", "Min Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25398", "source_url": "https://arxiv.org/abs/2608.25398"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "Evaluates multimodal physics understanding, reasoning, and generation on 15,246 questions with 19,850 images from middle-school to university levels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25398", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25398", "title": "OmniPhys"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.25398", "modality": null, "name": "OmniPhys", "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": "true", "origin_record_id": "bm_omniphys_ae437965", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6b3aef7c74e9e80f1ebc1fe1b6f40f2914912ee4ba87327cad237c882bd337bd", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:12:36.511123Z", "source_url": "https://arxiv.org/abs/2608.25398"}, "publisher": null, "released": "2026-08-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25398", "source_url": "https://arxiv.org/abs/2608.25398"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25398", "source": "claire_radar", "source_benchmark_id": "2608.25398", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/ECNU-RAIL/OmniPhys-EMNLP2026", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.25398", "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", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Peer-reviewed venue acceptance and a large multimodal dataset with Chinese educational coverage; domain may limit broader adoption.", "score": 65}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:12:36.511123Z", "inputHash": "cfeee56d6d1abc7b9597e93ad0b6d52394fe5dfb509da78d7d73b80444097a94", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce OmniPhys, a large-scale benchmark for multimodal physics understanding and reasoning", "canonicalNameSource": "abstract", "decisionReason": "OmniPhys is named in the abstract and linked to a GitHub repository with data and code, indicating a reusable public benchmark accepted to EMNLP 2026 Findings.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:12:36.511123Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal physics understanding, reasoning, and generation on 15,246 questions with 19,850 images from middle-school to university levels.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To fill this gap, we introduce OmniPhys, a large-scale benchmark for multimodal physics understanding and reasoning, covering middle school through university-level problems from Chinese Educational Corpora."}, "familyId": "bmf_1f087830f505", "firstSeenAt": "2026-08-27", "heat": null, "id": "bm_omniphys_ae437965", "indexedAt": "2026-08-27T04:12:10.575570Z", "industrySectors": [], "links": {"code": "https://github.com/ECNU-RAIL/OmniPhys-EMNLP2026", "data": null, "paper": "https://arxiv.org/abs/2608.25398", "pdf": "https://arxiv.org/pdf/2608.25398", "project": null, "report": "https://arxiv.org/abs/2608.25398"}, "metrics": [], "motivation": "Multimodal Large Language Models (MLLMs) have demonstrated strong abilities in solving diverse visual and textual reasoning tasks.", "name": "OmniPhys", "oneLine": "Evaluates multimodal physics understanding, reasoning, and generation on 15,246 questions with 19,850 images from middle-school to university levels.", "paperTitle": "OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corpora", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to Findings of EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.25398", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Findings of EMNLP 2026", "verifiedAt": "2026-08-27T04:12:10.575570Z"}, "publications": [], "publishers": [{"name": "ECNU-RAIL", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/ECNU-RAIL/OmniPhys-EMNLP2026"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 488, "score": 23}, "method": "attention-ranking-v13", "rank": 488, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-26", "source": {"authors": ["Hao Chen", "Yumin Lin", "Nadila Yushanjiang", "Xin Lin", "Min Zhang"], "categories": ["cs.CL"], "id": "2608.25398", "title": "OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corpora", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25398"}, "sourceUpdatedAt": "2026-08-26T05:51:12Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to Findings of EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-08-27T04:12:10.575570Z", "rawValue": "Accepted to Findings of EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.25398"}], "reviewStatus": "accepted", "venueName": "Findings of EMNLP 2026"}], "whyItMatters": "Fills the gap in comprehensive physics benchmarks for MLLMs, including structured diagram generation and fine-grained reasoning analysis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
