{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6CEXI57VNV2ICISFDHHVGMZHNL","short_pith_number":"pith:6CEXI57V","schema_version":"1.0","canonical_sha256":"f0897477f56d7481224519cf5333276ad487cc5e606cfc0522218fc7d15b9bbb","source":{"kind":"arxiv","id":"2501.17183","version":2},"attestation_state":"computed","paper":{"title":"LLM Evaluation Based on Aerospace Manufacturing Expertise: Automated Generation and Multi-Model Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beiming Liu, Haifeng Lin, Siteng Hu, Xiaohua Li, Zhengxin Zhang, Zhizhuo Cui","submitted_at":"2025-01-25T12:26:44Z","abstract_excerpt":"Aerospace manufacturing demands exceptionally high precision in technical parameters. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and QWen, in Natural Language Processing has sparked industry interest in their application to tasks including process design, material selection, and tool information retrieval. However, LLMs are prone to generating \"hallucinations\" in specialized domains, producing inaccurate or false information that poses significant risks to the quality of aerospace products and flight safety. This paper introduces a set of evaluation metrics tailo"},"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":"2501.17183","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T12:26:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8052b07659e5e143bd4fc97089c37414ab9868037cb2c6a8561239620df865ea","abstract_canon_sha256":"c0af8f73871ab1af39b97d54905e7108b7e62f7494db9865082dfb8ab9bc0a0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:28.869972Z","signature_b64":"xV8REzmxiQBpRueqP+Isrv3jag+jp4j54n9KA/LYFmLHUPIhaMFzhSQfAdSSAu3eivyRyrwBmqMnw4FdjfGmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0897477f56d7481224519cf5333276ad487cc5e606cfc0522218fc7d15b9bbb","last_reissued_at":"2026-07-05T10:08:28.869440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:28.869440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Evaluation Based on Aerospace Manufacturing Expertise: Automated Generation and Multi-Model Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beiming Liu, Haifeng Lin, Siteng Hu, Xiaohua Li, Zhengxin Zhang, Zhizhuo Cui","submitted_at":"2025-01-25T12:26:44Z","abstract_excerpt":"Aerospace manufacturing demands exceptionally high precision in technical parameters. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and QWen, in Natural Language Processing has sparked industry interest in their application to tasks including process design, material selection, and tool information retrieval. However, LLMs are prone to generating \"hallucinations\" in specialized domains, producing inaccurate or false information that poses significant risks to the quality of aerospace products and flight safety. This paper introduces a set of evaluation metrics tailo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17183","kind":"arxiv","version":2},"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/2501.17183/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":"2501.17183","created_at":"2026-07-05T10:08:28.869496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17183v2","created_at":"2026-07-05T10:08:28.869496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17183","created_at":"2026-07-05T10:08:28.869496+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CEXI57VNV2I","created_at":"2026-07-05T10:08:28.869496+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CEXI57VNV2ICISF","created_at":"2026-07-05T10:08:28.869496+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CEXI57V","created_at":"2026-07-05T10:08:28.869496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20420","citing_title":"CAMB: A comprehensive industrial LLM benchmark on civil aviation maintenance","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL","json":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL.json","graph_json":"https://pith.science/api/pith-number/6CEXI57VNV2ICISFDHHVGMZHNL/graph.json","events_json":"https://pith.science/api/pith-number/6CEXI57VNV2ICISFDHHVGMZHNL/events.json","paper":"https://pith.science/paper/6CEXI57V"},"agent_actions":{"view_html":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL","download_json":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL.json","view_paper":"https://pith.science/paper/6CEXI57V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17183&json=true","fetch_graph":"https://pith.science/api/pith-number/6CEXI57VNV2ICISFDHHVGMZHNL/graph.json","fetch_events":"https://pith.science/api/pith-number/6CEXI57VNV2ICISFDHHVGMZHNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL/action/storage_attestation","attest_author":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL/action/author_attestation","sign_citation":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL/action/citation_signature","submit_replication":"https://pith.science/pith/6CEXI57VNV2ICISFDHHVGMZHNL/action/replication_record"}},"created_at":"2026-07-05T10:08:28.869496+00:00","updated_at":"2026-07-05T10:08:28.869496+00:00"}