{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.05571", "kind": "paper", "url": "https://arxiv.org/abs/2607.05571"}], "authors": ["H. Chad Lane", "Bryson Kageler"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.05571", "source_url": "https://arxiv.org/abs/2607.05571"}, "categories": ["Code & Software", "Code generation", "General AI", "cs.AI"], "description": {"en": "CSTutorBench evaluates small language models as tutors in VEX VR block-based programming, with 17 scenario-based questions scored via a rubric and LLM-as-judge."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.05571", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.05571", "title": "CSTutorBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Illinois Urbana-Champaign"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.05571", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.05571", "source_url": "https://openalex.org/W7167691074"}, "key": "claire-radar:2607.05571", "modality": null, "name": "CSTutorBench", "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_cstutorbench_cf78c812", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "33362bae52f7ab91ee0f0e1313192a51fd2f12fb186354d3c0455cd3d1758756", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.05571"}, "publisher": null, "released": "2026-07-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.05571", "source_url": "https://arxiv.org/abs/2607.05571"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-05571", "source": "claire_radar", "source_benchmark_id": "2607.05571", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "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/2607.05571", "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": ["Code generation"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d042a9cc0d83045cb479a5562f2ff6a122de902e8ed06dd8373c6364e06c7f70", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CSTutorBench evaluates small language models as tutors in VEX VR block-based programming, with 17 scenario-based questions scored via a rubric and LLM-as-judge.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce CSTutorBench, a benchmark for evaluating language models as CS tutors in VEX VR, a block-based robotics environment."}, "familyId": "bmf_0e6e4bdbb6d8", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_cstutorbench_cf78c812", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.05571", "paper": "https://arxiv.org/abs/2607.05571", "pdf": "https://arxiv.org/pdf/2607.05571", "project": null, "report": "https://arxiv.org/abs/2607.05571"}, "metrics": [], "motivation": "Large language models are increasingly explored as AI tutors, yet deploying them in K-12 settings raises concerns around privacy, cost, and reliance on proprietary models.", "name": "CSTutorBench", "oneLine": "CSTutorBench evaluates small language models as tutors in VEX VR block-based programming, with 17 scenario-based questions scored via a rubric and LLM-as-judge.", "paperTitle": "CSTutorBench: Benchmarking Small Language Models as Tutors for Block-Based Programming", "primaryDomain": "General AI", "publication": {"evidence": "SLM4ED'26: The 1st Workshop of Small Language Models for Education (SLM4ED). AIED 2026. Seoul, Republic of Korea", "evidenceLevel": "strong-author-metadata", "evidenceUrl": "https://arxiv.org/abs/2607.05571", "source": "arxiv-journal-reference", "status": "publication_reported", "venue": "SLM4ED'26: The 1st Workshop of Small Language Models for Education (SLM4ED). AIED 2026. Seoul, Republic of Korea", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [{"evidence": [{"level": "strong-author-metadata", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "SLM4ED'26: The 1st Workshop of Small Language Models for Education (SLM4ED). AIED 2026. Seoul, Republic of Korea", "sourceType": "arxiv-journal-reference", "sourceUrl": "https://arxiv.org/abs/2607.05571"}], "publicationStatus": "published", "venueName": "SLM4ED'26: The 1st Workshop of Small Language Models for Education (SLM4ED). AIED 2026. Seoul, Republic of Korea"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-06", "source": {"authors": ["H. Chad Lane", "Bryson Kageler"], "categories": ["cs.AI", "cs.HC"], "id": "2607.05571", "title": "CSTutorBench: Benchmarking Small Language Models as Tutors for Block-Based Programming", "type": "arxiv", "url": "https://arxiv.org/abs/2607.05571"}, "sourceUpdatedAt": "2026-07-06T19:15:07Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the gap in evaluating SLMs for block-based programming tutoring, where models often lack domain-specific training."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
