{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2EIXQDRZEECQ53G2SGCHRG4LW7","short_pith_number":"pith:2EIXQDRZ","schema_version":"1.0","canonical_sha256":"d111780e3921050eecda9184789b8bb7eb7845161c7d904e103b4b0aacaa005c","source":{"kind":"arxiv","id":"2501.07924","version":1},"attestation_state":"computed","paper":{"title":"Exploring Aviation Incident Narratives Using Topic Modeling and Clustering Techniques","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aziida Nanyonga, Graham Wild, Hassan Wasswa, Keith Joiner, Ugur Turhan","submitted_at":"2025-01-14T08:23:15Z","abstract_excerpt":"Aviation safety is a global concern, requiring detailed investigations into incidents to understand contributing factors comprehensively. This study uses the National Transportation Safety Board (NTSB) dataset. It applies advanced natural language processing (NLP) techniques, including Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (pLSA), and K-means clustering. The main objectives are identifying latent themes, exploring semantic relationships, assessing probabilistic connections, and cluster "},"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":"2501.07924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-14T08:23:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f5f8e1ee35f91fc8d9012ef5119293c81824726c65f92f6b872dca27cdbf149","abstract_canon_sha256":"585d8d5b91817ad77f4462eda4bc0351b036dbd8b3cac336fe2657ee04dc4fee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:52.656532Z","signature_b64":"Fvi2bFVvuQG/Llf7P+KvZEiEnViwDg/9lztQrc+Ul3B8iH5/87kFMGfWPNn9zbinQWCkI3V9kDEd6EBolXcDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d111780e3921050eecda9184789b8bb7eb7845161c7d904e103b4b0aacaa005c","last_reissued_at":"2026-07-05T10:00:52.656093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:52.656093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Aviation Incident Narratives Using Topic Modeling and Clustering Techniques","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aziida Nanyonga, Graham Wild, Hassan Wasswa, Keith Joiner, Ugur Turhan","submitted_at":"2025-01-14T08:23:15Z","abstract_excerpt":"Aviation safety is a global concern, requiring detailed investigations into incidents to understand contributing factors comprehensively. This study uses the National Transportation Safety Board (NTSB) dataset. It applies advanced natural language processing (NLP) techniques, including Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (pLSA), and K-means clustering. The main objectives are identifying latent themes, exploring semantic relationships, assessing probabilistic connections, and cluster "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07924","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/2501.07924/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":"2501.07924","created_at":"2026-07-05T10:00:52.656146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07924v1","created_at":"2026-07-05T10:00:52.656146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07924","created_at":"2026-07-05T10:00:52.656146+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EIXQDRZEECQ","created_at":"2026-07-05T10:00:52.656146+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EIXQDRZEECQ53G2","created_at":"2026-07-05T10:00:52.656146+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EIXQDRZ","created_at":"2026-07-05T10:00:52.656146+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/2EIXQDRZEECQ53G2SGCHRG4LW7","json":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7.json","graph_json":"https://pith.science/api/pith-number/2EIXQDRZEECQ53G2SGCHRG4LW7/graph.json","events_json":"https://pith.science/api/pith-number/2EIXQDRZEECQ53G2SGCHRG4LW7/events.json","paper":"https://pith.science/paper/2EIXQDRZ"},"agent_actions":{"view_html":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7","download_json":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7.json","view_paper":"https://pith.science/paper/2EIXQDRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07924&json=true","fetch_graph":"https://pith.science/api/pith-number/2EIXQDRZEECQ53G2SGCHRG4LW7/graph.json","fetch_events":"https://pith.science/api/pith-number/2EIXQDRZEECQ53G2SGCHRG4LW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7/action/storage_attestation","attest_author":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7/action/author_attestation","sign_citation":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7/action/citation_signature","submit_replication":"https://pith.science/pith/2EIXQDRZEECQ53G2SGCHRG4LW7/action/replication_record"}},"created_at":"2026-07-05T10:00:52.656146+00:00","updated_at":"2026-07-05T10:00:52.656146+00:00"}