{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.20926", "kind": "paper", "url": "https://arxiv.org/abs/2607.20926"}], "authors": ["Yinhao Tang", "Youqing Fang", "Yanan Sun", "Wenran Liu", "Weiming Zhang", "Bin Liu", "Kuikun Liu", "Wenwei Zhang", "Kai Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.20926", "source_url": "https://arxiv.org/abs/2607.20926"}, "categories": ["General AI", "Reasoning", "Robotics & Embodied AI"], "description": {"en": "SciExplore evaluates scientific information-seeking and reasoning in LLMs and agents with four task types: scientific database navigation, ambiguous literature retrieval, missing reference completion, and cross-source structured knowledge synthesis, spanning 103 expert-curated tasks across more than ten scientific disciplines."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.20926", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.20926", "title": "SciExplore"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Science and Technology of China", "Shanghai Artificial Intelligence Laboratory"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.20926", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.20926", "source_url": "https://openalex.org/W7170493490"}, "key": "claire-radar:2607.20926", "modality": null, "name": "SciExplore", "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": "unknown", "origin_record_id": "bm_sciexplore_df25f831", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ac1ebbd9e6cd8756593cb20d079e14e9cfda6f350920efc09cd0699575683ec3", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.20926"}, "publisher": null, "released": "2026-07-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.20926", "source_url": "https://arxiv.org/abs/2607.20926"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-20926", "source": "claire_radar", "source_benchmark_id": "2607.20926", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Robotics & Embodied AI", "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": 2, "hfPaperUrl": "https://huggingface.co/papers/2607.20926", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "57d2d7f78bd5ff16fcdce1215b7d6fa62bd3fddeb61418c5fc8340d0e45d5b2b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SciExplore evaluates scientific information-seeking and reasoning in LLMs and agents with four task types: scientific database navigation, ambiguous literature retrieval, missing reference completion, and cross-source structured knowledge synthesis, spanning 103 expert-curated tasks across more than ten scientific disciplines.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce SciExplore, a benchmark designed to evaluate scientific information-seeking and reasoning capabilities of LLMs and agents."}, "familyId": "bmf_0a205bd9cb5c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_sciexplore_df25f831", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.20926", "paper": "https://arxiv.org/abs/2607.20926", "pdf": "https://arxiv.org/pdf/2607.20926", "project": null, "report": "https://arxiv.org/abs/2607.20926"}, "metrics": [], "motivation": "Scientific research involves complex information-seeking and reasoning workflows across heterogeneous sources.", "name": "SciExplore", "oneLine": "SciExplore evaluates scientific information-seeking and reasoning in LLMs and agents with four task types: scientific database navigation, ambiguous literature retrieval, missing reference completion, and cross-source structured knowledge synthesis, spanning 103 expert-curated tasks across more than ten scientific disciplines.", "paperTitle": "SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.20926", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "SciExplore Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.20926"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.19411886932144953, "value": 2}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 45}, "method": "attention-ranking-v13", "rank": null, "score": 45}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-23", "source": {"authors": ["Yinhao Tang", "Youqing Fang", "Yanan Sun", "Wenran Liu", "Weiming Zhang", "Bin Liu", "Kuikun Liu", "Wenwei Zhang", "Kai Chen"], "categories": ["cs.AI"], "id": "2607.20926", "title": "SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration", "type": "arxiv", "url": "https://arxiv.org/abs/2607.20926"}, "sourceUpdatedAt": "2026-07-23T05:17:00Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing benchmarks emphasize general-domain retrieval or static QA, leaving a gap in assessing realistic scientific workflows. SciExplore's progressive task complexity provides a way to compare model capabilities in entity-level reasoning, document identification, evidence grounding, and domain-level synthesis, informing deployment in scientific research contexts."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
