{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.00739", "kind": "paper", "url": "https://arxiv.org/abs/2608.00739"}], "authors": ["Nizam Kadir"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.00739", "source_url": "https://arxiv.org/abs/2608.00739"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "EduPluginBench is an executable benchmark for evaluating code-generation models on producing plugins that meet governed ecosystem requirements including least privilege, telemetry consent, provenance, and bounded failure. It uses 1,440 mutants and 120 clean references with staged admission levels P0-P4."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.00739", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.00739", "title": "EduPluginBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Singapore University of Technology and Design"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.00739", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.00739", "source_url": "https://openalex.org/W7172406393"}, "key": "claire-radar:2608.00739", "modality": null, "name": "EduPluginBench", "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_edupluginbench_5240df80", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "b17020c28715b95afbe6750ef505372ebfdc47123d5f5c45673d0a4a7faf381b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.00739"}, "publisher": null, "released": "2026-08-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.00739", "source_url": "https://arxiv.org/abs/2608.00739"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-00739", "source": "claire_radar", "source_benchmark_id": "2608.00739", "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/2608.00739", "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": [], "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": "2932025763fd783563ed3470cceefc30734d2540086e0a2ef320354e6012e47e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EduPluginBench is an executable benchmark for evaluating code-generation models on producing plugins that meet governed ecosystem requirements including least privilege, telemetry consent, provenance, and bounded failure. It uses 1,440 mutants and 120 clean references with staged admission levels P0-P4.", "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 EduPluginBench, an executable benchmark and staged admission method for generated plugins in governed software ecosystems."}, "familyId": "bmf_74fa30a0270a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_edupluginbench_5240df80", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.00739", "paper": "https://arxiv.org/abs/2608.00739", "pdf": "https://arxiv.org/pdf/2608.00739", "project": null, "report": "https://arxiv.org/abs/2608.00739"}, "metrics": [], "motivation": "Code-generation models can produce executable components, but compilation and functional tests do not establish compliance with least privilege, telemetry consent, provenance, privileged-write authority, lifecycle constraints, or bounded failure.", "name": "EduPluginBench", "oneLine": "EduPluginBench is an executable benchmark for evaluating code-generation models on producing plugins that meet governed ecosystem requirements including least privilege, telemetry consent, provenance, and bounded failure. It uses 1,440 mutants and 120 clean references with staged admission levels P0-P4.", "paperTitle": "EduPluginBench: Executable Assurance for AI-Generated Educational Plugins", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.00739", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.00739"}], "ranking": {"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": 0.85, "relation": "introduces", "releasedAt": "2026-08-01", "source": {"authors": ["Nizam Kadir"], "categories": ["cs.SE", "cs.AI"], "id": "2608.00739", "title": "EduPluginBench: Executable Assurance for AI-Generated Educational Plugins", "type": "arxiv", "url": "https://arxiv.org/abs/2608.00739"}, "sourceUpdatedAt": "2026-08-01T16:22:35Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Compilation and functional tests do not ensure compliance with security and governance constraints. EduPluginBench provides a staged admission method targeting these gaps, enabling assessment of generated plugins in governed environments, which is critical for safe deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
