{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03144", "kind": "paper", "url": "https://arxiv.org/abs/2606.03144"}], "authors": ["Noujoud Nader", "Ibrahem Aljabea", "Patrick Diehl", "Deepti Gupta"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03144", "source_url": "https://arxiv.org/abs/2606.03144"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "GTBench is a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, with problems across three difficulty groups."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03144", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03144", "title": "GTBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Louisiana State University", "Los Alamos National Laboratory"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.03144", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.03144", "source_url": "https://openalex.org/W7163344630"}, "key": "claire-radar:2606.03144", "modality": null, "name": "GTBench", "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": "unknown", "origin_record_id": "bm_gtbench_117f8151", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "2d758a541c97dee9ebec3b3dd8f474009cafb70228bc58011f11f9ee26233451", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03144"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03144", "source_url": "https://arxiv.org/abs/2606.03144"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03144", "source": "claire_radar", "source_benchmark_id": "2606.03144", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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/2606.03144", "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"}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3207b65649ae147fce81ae4e0f6d22067808f5d9aa62311cba32944cb66deccc", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GTBench is a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, with problems across three difficulty groups.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce GTBench, a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, comprising 63 problems organized into three groups of increasing difficulty: undergraduate definitions and basic properties (Group 1), algorithm tracing and structural reasoning (Group 2), and graduate-level proof construction (Group 3)."}, "familyId": "bmf_ed4666e9eda2", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_gtbench_117f8151", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.03144", "paper": "https://arxiv.org/abs/2606.03144", "pdf": "https://arxiv.org/pdf/2606.03144", "project": null, "report": "https://arxiv.org/abs/2606.03144"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly understood.", "name": "GTBench", "oneLine": "GTBench is a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, with problems across three difficulty groups.", "paperTitle": "GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03144", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Noujoud Nader", "Ibrahem Aljabea", "Patrick Diehl", "Deepti Gupta"], "categories": ["cs.AI"], "id": "2606.03144", "title": "GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03144"}, "sourceUpdatedAt": "2026-06-02T04:40:25Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "It reveals performance gaps in graph-theoretic reasoning among frontier models, informing the use of AI in education and research."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
