{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.01829", "kind": "paper", "url": "https://arxiv.org/abs/2607.01829"}], "authors": ["Alex Brooker", "Tim Hughes"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.01829", "source_url": "https://arxiv.org/abs/2607.01829"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Pre-Flight evaluates large language models on aviation operational knowledge via 300 multiple-choice questions drawn from international standards and airport ground operations material, covering ground operations, ICAO and FAA regulations, general aviation knowledge, and operational scenarios. Scoring is by accuracy under a standard multiple-choice protocol using the Inspect framework."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.01829", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.01829", "title": "Pre-Flight"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.01829", "modality": null, "name": "Pre-Flight", "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_pre-flight_898fa920", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5ccd16e768ab1d68e2e3708e42d0d24c5f371163c8784afd66da69977fc2807a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.01829"}, "publisher": null, "released": "2026-07-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.01829", "source_url": "https://arxiv.org/abs/2607.01829"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-01829", "source": "claire_radar", "source_benchmark_id": "2607.01829", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.01829", "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", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "status": "stale"}, "capabilities": ["Factuality"], "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": "332b08eb0dc49f79dece7a81c9299b4606050beeee64e140a8bdfc4a9c611587", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Pre-Flight evaluates large language models on aviation operational knowledge via 300 multiple-choice questions drawn from international standards and airport ground operations material, covering ground operations, ICAO and FAA regulations, general aviation knowledge, and operational scenarios. Scoring is by accuracy under a standard multiple-choice protocol using the Inspect framework.", "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 present Pre-Flight, an open source benchmark of 300 multiple choice questions drawn from international standards and airport ground operations material, covering international airport ground operations, ICAO and US FAA regulations, aviation general knowledge and complex operational scenarios."}, "familyId": "bmf_6f851dc66002", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_pre-flight_898fa920", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.01829", "paper": "https://arxiv.org/abs/2607.01829", "pdf": "https://arxiv.org/pdf/2607.01829", "project": null, "report": "https://arxiv.org/abs/2607.01829"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly proposed for aviation business operations, from documentation and training generation to customer facing assistants.", "name": "Pre-Flight", "oneLine": "Pre-Flight evaluates large language models on aviation operational knowledge via 300 multiple-choice questions drawn from international standards and airport ground operations material, covering ground operations, ICAO and FAA regulations, general aviation knowledge, and operational scenarios. Scoring is by accuracy under a standard multiple-choice protocol using the Inspect framework.", "paperTitle": "Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.01829", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-02", "source": {"authors": ["Alex Brooker", "Tim Hughes"], "categories": ["cs.AI", "cs.CL"], "id": "2607.01829", "title": "Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge", "type": "arxiv", "url": "https://arxiv.org/abs/2607.01829"}, "sourceUpdatedAt": "2026-07-02T07:49:55Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "General-purpose benchmarks do not assess aviation-specific operational safety knowledge, a high-stakes domain where incorrect reasoning can have serious consequences. This benchmark provides a domain-specific evaluation to gauge model reliability for non-safety-critical aviation operations."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
