{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZX3ZV2AMWIEZUZSNZEM4K63PVR","short_pith_number":"pith:ZX3ZV2AM","schema_version":"1.0","canonical_sha256":"cdf79ae80cb2099a664dc919c57b6fac4366936a801725dad0755b38a61a1675","source":{"kind":"arxiv","id":"2109.01949","version":1},"attestation_state":"computed","paper":{"title":"Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Dana Moukheiber, Mingchen Gao, Mohammad Abuzar Shaikh, Sargur Srihari, Yifan Peng, Zhanghexuan Ji","submitted_at":"2021-09-04T22:58:35Z","abstract_excerpt":"Self-supervised learning provides an opportunity to explore unlabeled chest X-rays and their associated free-text reports accumulated in clinical routine without manual supervision. This paper proposes a Joint Image Text Representation Learning Network (JoImTeRNet) for pre-training on chest X-ray images and their radiology reports. The model was pre-trained on both the global image-sentence level and the local image region-word level for visual-textual matching. Both are bidirectionally constrained on Cross-Entropy based and ranking-based Triplet Matching Losses. The region-word matching is ca"},"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":"2109.01949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-04T22:58:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.IV"],"title_canon_sha256":"7de8e6053b85fd0ef99818f5dd1e31995f8289cd800de793604506b17cc0e078","abstract_canon_sha256":"39bcae59524316d75264bd5da785f63fee2099da96bf37c9ecd7b353f986baae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:36.734872Z","signature_b64":"gbDMiibiVZpJjlRPsxRW0I3TgsVA6kdjHUsyYYEyyWo30mCuQamErE3fjw39QUdgdSvPnsXgpmHsS7vk+DLkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdf79ae80cb2099a664dc919c57b6fac4366936a801725dad0755b38a61a1675","last_reissued_at":"2026-07-05T03:11:36.734479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:36.734479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Dana Moukheiber, Mingchen Gao, Mohammad Abuzar Shaikh, Sargur Srihari, Yifan Peng, Zhanghexuan Ji","submitted_at":"2021-09-04T22:58:35Z","abstract_excerpt":"Self-supervised learning provides an opportunity to explore unlabeled chest X-rays and their associated free-text reports accumulated in clinical routine without manual supervision. This paper proposes a Joint Image Text Representation Learning Network (JoImTeRNet) for pre-training on chest X-ray images and their radiology reports. The model was pre-trained on both the global image-sentence level and the local image region-word level for visual-textual matching. Both are bidirectionally constrained on Cross-Entropy based and ranking-based Triplet Matching Losses. The region-word matching is ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01949","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/2109.01949/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":"2109.01949","created_at":"2026-07-05T03:11:36.734537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01949v1","created_at":"2026-07-05T03:11:36.734537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01949","created_at":"2026-07-05T03:11:36.734537+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZX3ZV2AMWIEZ","created_at":"2026-07-05T03:11:36.734537+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZX3ZV2AMWIEZUZSN","created_at":"2026-07-05T03:11:36.734537+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZX3ZV2AM","created_at":"2026-07-05T03:11:36.734537+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/ZX3ZV2AMWIEZUZSNZEM4K63PVR","json":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR.json","graph_json":"https://pith.science/api/pith-number/ZX3ZV2AMWIEZUZSNZEM4K63PVR/graph.json","events_json":"https://pith.science/api/pith-number/ZX3ZV2AMWIEZUZSNZEM4K63PVR/events.json","paper":"https://pith.science/paper/ZX3ZV2AM"},"agent_actions":{"view_html":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR","download_json":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR.json","view_paper":"https://pith.science/paper/ZX3ZV2AM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01949&json=true","fetch_graph":"https://pith.science/api/pith-number/ZX3ZV2AMWIEZUZSNZEM4K63PVR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZX3ZV2AMWIEZUZSNZEM4K63PVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR/action/storage_attestation","attest_author":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR/action/author_attestation","sign_citation":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR/action/citation_signature","submit_replication":"https://pith.science/pith/ZX3ZV2AMWIEZUZSNZEM4K63PVR/action/replication_record"}},"created_at":"2026-07-05T03:11:36.734537+00:00","updated_at":"2026-07-05T03:11:36.734537+00:00"}