{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7INRE4UUDHIBP72XIYCQGM2XEC","short_pith_number":"pith:7INRE4UU","schema_version":"1.0","canonical_sha256":"fa1b12729419d017ff57460503335720b510e5bd4f3b0426dca75a1ab700a447","source":{"kind":"arxiv","id":"2506.13785","version":1},"attestation_state":"computed","paper":{"title":"LLM-Driven Data Generation and a Novel Soft Metric for Evaluating Text-to-SQL in Aviation MRO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Joan Santoso, Jonathan Kenrick, Max Lorenz, Patrick Sutanto","submitted_at":"2025-06-11T04:04:13Z","abstract_excerpt":"The application of Large Language Models (LLMs) to text-to-SQL tasks promises to democratize data access, particularly in critical industries like aviation Maintenance, Repair, and Operation (MRO). However, progress is hindered by two key challenges: the rigidity of conventional evaluation metrics such as execution accuracy, which offer coarse, binary feedback, and the scarcity of domain-specific evaluation datasets. This paper addresses these gaps. To enable more nuanced assessment, we introduce a novel F1-score-based 'soft' metric that quantifies the informational overlap between generated a"},"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":"2506.13785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-11T04:04:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"608940d2355be0e6f2d6ea0cd367c500fc014c044803bb424b8d77f17a3b22f0","abstract_canon_sha256":"b20eaa2f9fbbb08838e83585e2b760c20e718522c33e4c0d7041f4f6f23c2182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:43.320597Z","signature_b64":"Gs/ZaQnHRV2+w6whQ2cytrpNEkjbVO4fcdk0tHHKCGXz+WqiNXuVf0kEgpWiOcBn8D3HyNxi0UwWoEC4vujGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa1b12729419d017ff57460503335720b510e5bd4f3b0426dca75a1ab700a447","last_reissued_at":"2026-07-05T11:22:43.320121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:43.320121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Driven Data Generation and a Novel Soft Metric for Evaluating Text-to-SQL in Aviation MRO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Joan Santoso, Jonathan Kenrick, Max Lorenz, Patrick Sutanto","submitted_at":"2025-06-11T04:04:13Z","abstract_excerpt":"The application of Large Language Models (LLMs) to text-to-SQL tasks promises to democratize data access, particularly in critical industries like aviation Maintenance, Repair, and Operation (MRO). However, progress is hindered by two key challenges: the rigidity of conventional evaluation metrics such as execution accuracy, which offer coarse, binary feedback, and the scarcity of domain-specific evaluation datasets. This paper addresses these gaps. To enable more nuanced assessment, we introduce a novel F1-score-based 'soft' metric that quantifies the informational overlap between generated a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13785","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/2506.13785/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":"2506.13785","created_at":"2026-07-05T11:22:43.320179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13785v1","created_at":"2026-07-05T11:22:43.320179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13785","created_at":"2026-07-05T11:22:43.320179+00:00"},{"alias_kind":"pith_short_12","alias_value":"7INRE4UUDHIB","created_at":"2026-07-05T11:22:43.320179+00:00"},{"alias_kind":"pith_short_16","alias_value":"7INRE4UUDHIBP72X","created_at":"2026-07-05T11:22:43.320179+00:00"},{"alias_kind":"pith_short_8","alias_value":"7INRE4UU","created_at":"2026-07-05T11:22:43.320179+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/7INRE4UUDHIBP72XIYCQGM2XEC","json":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC.json","graph_json":"https://pith.science/api/pith-number/7INRE4UUDHIBP72XIYCQGM2XEC/graph.json","events_json":"https://pith.science/api/pith-number/7INRE4UUDHIBP72XIYCQGM2XEC/events.json","paper":"https://pith.science/paper/7INRE4UU"},"agent_actions":{"view_html":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC","download_json":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC.json","view_paper":"https://pith.science/paper/7INRE4UU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13785&json=true","fetch_graph":"https://pith.science/api/pith-number/7INRE4UUDHIBP72XIYCQGM2XEC/graph.json","fetch_events":"https://pith.science/api/pith-number/7INRE4UUDHIBP72XIYCQGM2XEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC/action/storage_attestation","attest_author":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC/action/author_attestation","sign_citation":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC/action/citation_signature","submit_replication":"https://pith.science/pith/7INRE4UUDHIBP72XIYCQGM2XEC/action/replication_record"}},"created_at":"2026-07-05T11:22:43.320179+00:00","updated_at":"2026-07-05T11:22:43.320179+00:00"}