{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XTAEW6QLLG466BHLZ62BUJWYIU","short_pith_number":"pith:XTAEW6QL","schema_version":"1.0","canonical_sha256":"bcc04b7a0b59b9ef04ebcfb41a26d8450c58a32cde23d7a3f0e4ff21889cce15","source":{"kind":"arxiv","id":"2408.16068","version":2},"attestation_state":"computed","paper":{"title":"Identification of Prognostic Biomarkers for Stage III Non-Small Cell Lung Carcinoma in Female Nonsmokers Using Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"q-bio.GN","authors_text":"Huili Zheng, Qimin Zhang, Shaohan Chen, Yiru Gong, Zheyan Liu","submitted_at":"2024-08-28T18:08:11Z","abstract_excerpt":"Lung cancer remains a leading cause of cancer-related deaths globally, with non-small cell lung cancer (NSCLC) being the most common subtype. This study aimed to identify key biomarkers associated with stage III NSCLC in non-smoking females using gene expression profiling from the GDS3837 dataset. Utilizing XGBoost, a machine learning algorithm, the analysis achieved a strong predictive performance with an AUC score of 0.835. The top biomarkers identified - CCAAT enhancer binding protein alpha (C/EBP-alpha), lactate dehydrogenase A4 (LDHA), UNC-45 myosin chaperone B (UNC-45B), checkpoint kinas"},"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":"2408.16068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-08-28T18:08:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"efe6ed0664327612a8349553572582409d55f6e42780bf91506b86f1f6129035","abstract_canon_sha256":"590651f073a49d0a76b6c2931d5a22f13b3467f38bea96b24a51281c95f83db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:05.441818Z","signature_b64":"IK0bVzuGquu+LtVpM+OR0DXFUtjEFX2Jgq+99hOgbzEUgeTEx9c58CYa5SYcW4nmReOp0MHHfzkTwbX2DzutAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc04b7a0b59b9ef04ebcfb41a26d8450c58a32cde23d7a3f0e4ff21889cce15","last_reissued_at":"2026-07-05T09:01:05.441362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:05.441362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identification of Prognostic Biomarkers for Stage III Non-Small Cell Lung Carcinoma in Female Nonsmokers Using Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"q-bio.GN","authors_text":"Huili Zheng, Qimin Zhang, Shaohan Chen, Yiru Gong, Zheyan Liu","submitted_at":"2024-08-28T18:08:11Z","abstract_excerpt":"Lung cancer remains a leading cause of cancer-related deaths globally, with non-small cell lung cancer (NSCLC) being the most common subtype. This study aimed to identify key biomarkers associated with stage III NSCLC in non-smoking females using gene expression profiling from the GDS3837 dataset. Utilizing XGBoost, a machine learning algorithm, the analysis achieved a strong predictive performance with an AUC score of 0.835. The top biomarkers identified - CCAAT enhancer binding protein alpha (C/EBP-alpha), lactate dehydrogenase A4 (LDHA), UNC-45 myosin chaperone B (UNC-45B), checkpoint kinas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16068","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/2408.16068/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":"2408.16068","created_at":"2026-07-05T09:01:05.441426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16068v2","created_at":"2026-07-05T09:01:05.441426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16068","created_at":"2026-07-05T09:01:05.441426+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTAEW6QLLG46","created_at":"2026-07-05T09:01:05.441426+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTAEW6QLLG466BHL","created_at":"2026-07-05T09:01:05.441426+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTAEW6QL","created_at":"2026-07-05T09:01:05.441426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10567","citing_title":"Cardiovascular Disease Detection By Leveraging Semi-Supervised Learning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU","json":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU.json","graph_json":"https://pith.science/api/pith-number/XTAEW6QLLG466BHLZ62BUJWYIU/graph.json","events_json":"https://pith.science/api/pith-number/XTAEW6QLLG466BHLZ62BUJWYIU/events.json","paper":"https://pith.science/paper/XTAEW6QL"},"agent_actions":{"view_html":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU","download_json":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU.json","view_paper":"https://pith.science/paper/XTAEW6QL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16068&json=true","fetch_graph":"https://pith.science/api/pith-number/XTAEW6QLLG466BHLZ62BUJWYIU/graph.json","fetch_events":"https://pith.science/api/pith-number/XTAEW6QLLG466BHLZ62BUJWYIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU/action/storage_attestation","attest_author":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU/action/author_attestation","sign_citation":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU/action/citation_signature","submit_replication":"https://pith.science/pith/XTAEW6QLLG466BHLZ62BUJWYIU/action/replication_record"}},"created_at":"2026-07-05T09:01:05.441426+00:00","updated_at":"2026-07-05T09:01:05.441426+00:00"}