{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.11243", "kind": "paper", "url": "https://arxiv.org/abs/2609.11243"}], "authors": ["Jiaqiang Li", "Yajie Yang", "Zhiheng Xi", "Jiadong Chen", "Enyu Zhou", "Senjie Jin", "Yang Nan", "Jiazheng Zhang", "Han Wang", "Yanxin Li", "Dingwei Zhu", "Bicheng Deng", "Yuhui Wang", "Xiang Zheng", "Qi Zhang", "Lei Bai", "Xingjun Ma", "Tao Gui"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.11243", "source_url": "https://arxiv.org/abs/2609.11243"}, "categories": ["Factuality", "General AI", "Multimodal", "Reasoning"], "description": {"en": "Evaluation of multi-step evidence-grounded scientific reasoning in multimodal agents using structured argument graphs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.11243", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.11243", "title": "Sci-MMR"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.11243", "modality": null, "name": "Sci-MMR", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_sci-mmr_5e81a2e1", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "31726cd2622c23a375d2c5d843e2ca8fe37acb99e9aabc2565788226d603ec4e", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T00:43:53.625753Z", "source_url": "https://arxiv.org/abs/2609.11243"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.11243", "source_url": "https://arxiv.org/abs/2609.11243"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-11243", "source": "claire_radar", "source_benchmark_id": "2609.11243", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-09-12", "attemptedAt": "2026-09-12T01:46:06.616968Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.11243", "observedAt": "2026-09-11T12:23:23.267513Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-12T01:46:06.616968Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Without artifacts or community signals, early attention is expected to be very low.", "score": 0}, "capabilities": ["Reasoning", "Factuality"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T00:43:53.625753Z", "inputHash": "ff2ea3a891d9e6673023156d4dc84cb40df14b5a2a67eddaa2a40b8d5ced8271", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We introduce Sci-MMR, a benchmark for multi-step evidence-grounded scientific reasoning built on structured argument graphs linking scientific claims, citation-grounded knowledge, visual evidence, and supporting regions.", "canonicalNameSource": "abstract", "decisionReason": "The paper introduces a benchmark but provides no artifact evidence or public path details in the supplied information.", "evaluationEvidence": {"reuse": "The paper is presented as a benchmark, and the abstract asserts it is introduced; however, no explicit evidence is provided about released datasets, code, documentation, or an external submission path.", "scoring": "The benchmark is built on structured argument graphs, implying a formally defined evaluation of reasoning steps and evidence grounding, though the abstract does not specify the exact metric names or scoring function.", "task": "Multi-step evidence-grounded scientific reasoning over structured argument graphs that include scientific claims, citation-grounded knowledge, visual evidence, and supporting regions."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-14T00:43:53.625753Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluation of multi-step evidence-grounded scientific reasoning in multimodal agents using structured argument graphs.", "displayEligible": false, "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"], "snippet": "We introduce Sci-MMR, a benchmark for multi-step evidence-grounded scientific reasoning built on structured argument graphs linking scientific claims, citation-grounded knowledge, visual evidence, and supporting regions."}, "familyId": "bmf_3d437d86dc25", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_sci-mmr_5e81a2e1", "indexedAt": "2026-09-11T00:48:15.671466Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.11243", "pdf": "https://arxiv.org/pdf/2609.11243", "project": null, "report": "https://arxiv.org/abs/2609.11243"}, "metrics": [], "motivation": "Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses.", "name": "Sci-MMR", "oneLine": "Evaluation of multi-step evidence-grounded scientific reasoning in multimodal agents using structured argument graphs.", "paperTitle": "Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.11243", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-11T00:48:15.671466Z"}, "publications": [], "ranking": {"30d": {"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": 30}, "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}, "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": 1.0, "relation": "introduces", "releasedAt": "2026-09-10", "source": {"authors": ["Jiaqiang Li", "Yajie Yang", "Zhiheng Xi", "Jiadong Chen", "Enyu Zhou", "Senjie Jin", "Yang Nan", "Jiazheng Zhang", "Han Wang", "Yanxin Li", "Dingwei Zhu", "Bicheng Deng", "Yuhui Wang", "Xiang Zheng", "Qi Zhang", "Lei Bai", "Xingjun Ma", "Tao Gui"], "categories": ["cs.AI"], "id": "2609.11243", "title": "Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2609.11243"}, "sourceUpdatedAt": "2026-09-10T08:41:07Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "Assesses agents' ability to chain scientific claims, citations, and visual evidence under explicit dependency structure."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
