{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZLBWI6RUH3HJQZ3ZXRKFIMDR3","short_pith_number":"pith:AZLBWI6R","schema_version":"1.0","canonical_sha256":"06561b23d1a1f674c33bcde2a2a1838ee9bb030dbcc1227fc8abf972c877b6ce","source":{"kind":"arxiv","id":"2607.01829","version":1},"attestation_state":"computed","paper":{"title":"Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Alex Brooker, Tim Hughes","submitted_at":"2026-07-02T07:49:55Z","abstract_excerpt":"Large language models (LLMs) are increasingly proposed for aviation business operations, from documentation and training generation to customer facing assistants. General purpose benchmarks do not measure whether a model reasons safely and correctly about aviation specific operational knowledge, and the high stakes, regulated nature of the domain makes that gap consequential. 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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.01829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T07:49:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"55fe282aa3e4a2e23b1d3559d3d0a947280416a8adc719a97e2c62ffd086285f","abstract_canon_sha256":"7069d9e792e889fb999f674e7fb793c8160e977ed7f48aa8b6ee622db2be50c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:31.033853Z","signature_b64":"9SHGGy91Eyw4ydooKcyR3dkBDC4ATJOITsjGGlkEc/DM79hd3yYCAYHHAmqG335G+IlFK8CvSMhpztV/7xsyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06561b23d1a1f674c33bcde2a2a1838ee9bb030dbcc1227fc8abf972c877b6ce","last_reissued_at":"2026-07-03T01:17:31.033441Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:31.033441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Alex Brooker, Tim Hughes","submitted_at":"2026-07-02T07:49:55Z","abstract_excerpt":"Large language models (LLMs) are increasingly proposed for aviation business operations, from documentation and training generation to customer facing assistants. General purpose benchmarks do not measure whether a model reasons safely and correctly about aviation specific operational knowledge, and the high stakes, regulated nature of the domain makes that gap consequential. 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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01829","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.01829/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.01829","created_at":"2026-07-03T01:17:31.033504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01829v1","created_at":"2026-07-03T01:17:31.033504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01829","created_at":"2026-07-03T01:17:31.033504+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZLBWI6RUH3H","created_at":"2026-07-03T01:17:31.033504+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZLBWI6RUH3HJQZ3","created_at":"2026-07-03T01:17:31.033504+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZLBWI6R","created_at":"2026-07-03T01:17:31.033504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3","json":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3.json","graph_json":"https://pith.science/api/pith-number/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/graph.json","events_json":"https://pith.science/api/pith-number/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/events.json","paper":"https://pith.science/paper/AZLBWI6R"},"agent_actions":{"view_html":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3","download_json":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3.json","view_paper":"https://pith.science/paper/AZLBWI6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01829&json=true","fetch_graph":"https://pith.science/api/pith-number/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/graph.json","fetch_events":"https://pith.science/api/pith-number/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/action/storage_attestation","attest_author":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/action/author_attestation","sign_citation":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/action/citation_signature","submit_replication":"https://pith.science/pith/AZLBWI6RUH3HJQZ3ZXRKFIMDR3/action/replication_record"}},"created_at":"2026-07-03T01:17:31.033504+00:00","updated_at":"2026-07-03T01:17:31.033504+00:00"}