{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RG7INBNOYF3OTH224PO2FTZFKD","short_pith_number":"pith:RG7INBNO","schema_version":"1.0","canonical_sha256":"89be8685aec176e99f5ae3dda2cf2550d99c40543622f81a68be961ff74c0ff4","source":{"kind":"arxiv","id":"2105.07540","version":2},"attestation_state":"computed","paper":{"title":"Deep learning for detecting pulmonary tuberculosis via chest radiography: an international study across 10 countries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Atilla Kiraly, Charles Lau, Christina Chen, Daniel Tse, Greg S. Corrado, Jameson Malemela, Jin Yu, Katherine Chou, Krish Eswaran, Lily Peng, Monde Muyoyeta, Neeral Beladia, Po-Hsuan Cameron Chen, Rory Pilgrim, Sahar Kazemzadeh, Scott Mayer McKinney, Shahar Jamshy, Shravya Shetty, Shruthi Prabhakara, Sreenivasa Raju Kalidindi, Thad Hughes, Ting Shih, Yun Liu, Zaid Nabulsi","submitted_at":"2021-05-16T22:56:06Z","abstract_excerpt":"Tuberculosis (TB) is a top-10 cause of death worldwide. Though the WHO recommends chest radiographs (CXRs) for TB screening, the limited availability of CXR interpretation is a barrier. We trained a deep learning system (DLS) to detect active pulmonary TB using CXRs from 9 countries across Africa, Asia, and Europe, and utilized large-scale CXR pretraining, attention pooling, and noisy student semi-supervised learning. Evaluation was on (1) a combined test set spanning China, India, US, and Zambia, and (2) an independent mining population in South Africa. Given WHO targets of 90% sensitivity an"},"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":"2105.07540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-05-16T22:56:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"dd8f1e871ce0c169e57641dba747fff15ed6712a18f9cad7fa07b4f7a02bcd19","abstract_canon_sha256":"cfe4168571e2a9fa6ff5be0771f5b9ec4b4c65d755c1f61e83a3a43f3d880cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:31.628685Z","signature_b64":"Q+2EdirsevL987MYYboO5I88HfRbc7G2r6PdWtqUcnokSoU5QM9H5+AuvZF2ytdAChYmMkK3sUf3kXyaQecMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89be8685aec176e99f5ae3dda2cf2550d99c40543622f81a68be961ff74c0ff4","last_reissued_at":"2026-07-05T03:27:31.628208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:31.628208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep learning for detecting pulmonary tuberculosis via chest radiography: an international study across 10 countries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Atilla Kiraly, Charles Lau, Christina Chen, Daniel Tse, Greg S. Corrado, Jameson Malemela, Jin Yu, Katherine Chou, Krish Eswaran, Lily Peng, Monde Muyoyeta, Neeral Beladia, Po-Hsuan Cameron Chen, Rory Pilgrim, Sahar Kazemzadeh, Scott Mayer McKinney, Shahar Jamshy, Shravya Shetty, Shruthi Prabhakara, Sreenivasa Raju Kalidindi, Thad Hughes, Ting Shih, Yun Liu, Zaid Nabulsi","submitted_at":"2021-05-16T22:56:06Z","abstract_excerpt":"Tuberculosis (TB) is a top-10 cause of death worldwide. Though the WHO recommends chest radiographs (CXRs) for TB screening, the limited availability of CXR interpretation is a barrier. We trained a deep learning system (DLS) to detect active pulmonary TB using CXRs from 9 countries across Africa, Asia, and Europe, and utilized large-scale CXR pretraining, attention pooling, and noisy student semi-supervised learning. Evaluation was on (1) a combined test set spanning China, India, US, and Zambia, and (2) an independent mining population in South Africa. Given WHO targets of 90% sensitivity an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07540","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/2105.07540/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":"2105.07540","created_at":"2026-07-05T03:27:31.628268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07540v2","created_at":"2026-07-05T03:27:31.628268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07540","created_at":"2026-07-05T03:27:31.628268+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG7INBNOYF3O","created_at":"2026-07-05T03:27:31.628268+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG7INBNOYF3OTH22","created_at":"2026-07-05T03:27:31.628268+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG7INBNO","created_at":"2026-07-05T03:27:31.628268+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/RG7INBNOYF3OTH224PO2FTZFKD","json":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD.json","graph_json":"https://pith.science/api/pith-number/RG7INBNOYF3OTH224PO2FTZFKD/graph.json","events_json":"https://pith.science/api/pith-number/RG7INBNOYF3OTH224PO2FTZFKD/events.json","paper":"https://pith.science/paper/RG7INBNO"},"agent_actions":{"view_html":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD","download_json":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD.json","view_paper":"https://pith.science/paper/RG7INBNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07540&json=true","fetch_graph":"https://pith.science/api/pith-number/RG7INBNOYF3OTH224PO2FTZFKD/graph.json","fetch_events":"https://pith.science/api/pith-number/RG7INBNOYF3OTH224PO2FTZFKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD/action/storage_attestation","attest_author":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD/action/author_attestation","sign_citation":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD/action/citation_signature","submit_replication":"https://pith.science/pith/RG7INBNOYF3OTH224PO2FTZFKD/action/replication_record"}},"created_at":"2026-07-05T03:27:31.628268+00:00","updated_at":"2026-07-05T03:27:31.628268+00:00"}