{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HYABUQRXYEW5L4NRN3MDIQKBYM","short_pith_number":"pith:HYABUQRX","schema_version":"1.0","canonical_sha256":"3e001a4237c12dd5f1b16ed8344141c323fa1f2febaf3525dadf629e434fc9dc","source":{"kind":"arxiv","id":"2407.12064","version":1},"attestation_state":"computed","paper":{"title":"LiteGPT: Large Vision-Language Model for Joint Chest X-ray Localization and Classification Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM"],"primary_cat":"eess.IV","authors_text":"Anh Dao, Anh Totti Nguyen, Ba Hung Ngo, Khai Le-Duc, Ngoc Son Nguyen, Ryan Zhang, Tan-Hanh Pham, Truong-Son Hy","submitted_at":"2024-07-16T02:19:02Z","abstract_excerpt":"Vision-language models have been extensively explored across a wide range of tasks, achieving satisfactory performance; however, their application in medical imaging remains underexplored. In this work, we propose a unified framework - LiteGPT - for the medical imaging. We leverage multiple pre-trained visual encoders to enrich information and enhance the performance of vision-language models. To the best of our knowledge, this is the first study to utilize vision-language models for the novel task of joint localization and classification in medical images. Besides, we are pioneers in providin"},"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":"2407.12064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-07-16T02:19:02Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"d84d1e57eac62b7b62ecc5f8a99ed8b40019df8dadfca75dbd7536b01a221277","abstract_canon_sha256":"78d25eda207f360fa517821cfa729ac53841e77ea0c3e073e9bd969b5ce281fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:59.590422Z","signature_b64":"to+NVVyV+84EcBjMeNVVWcwATBhzEKYVtIa3wsk3jloAhQ84fsMHAB9AgHoGv4hVmoj/LdX1+x6O0peXfT1pBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e001a4237c12dd5f1b16ed8344141c323fa1f2febaf3525dadf629e434fc9dc","last_reissued_at":"2026-07-05T08:44:59.590034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:59.590034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiteGPT: Large Vision-Language Model for Joint Chest X-ray Localization and Classification Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM"],"primary_cat":"eess.IV","authors_text":"Anh Dao, Anh Totti Nguyen, Ba Hung Ngo, Khai Le-Duc, Ngoc Son Nguyen, Ryan Zhang, Tan-Hanh Pham, Truong-Son Hy","submitted_at":"2024-07-16T02:19:02Z","abstract_excerpt":"Vision-language models have been extensively explored across a wide range of tasks, achieving satisfactory performance; however, their application in medical imaging remains underexplored. In this work, we propose a unified framework - LiteGPT - for the medical imaging. We leverage multiple pre-trained visual encoders to enrich information and enhance the performance of vision-language models. To the best of our knowledge, this is the first study to utilize vision-language models for the novel task of joint localization and classification in medical images. Besides, we are pioneers in providin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12064","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/2407.12064/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":"2407.12064","created_at":"2026-07-05T08:44:59.590089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12064v1","created_at":"2026-07-05T08:44:59.590089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12064","created_at":"2026-07-05T08:44:59.590089+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYABUQRXYEW5","created_at":"2026-07-05T08:44:59.590089+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYABUQRXYEW5L4NR","created_at":"2026-07-05T08:44:59.590089+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYABUQRX","created_at":"2026-07-05T08:44:59.590089+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/HYABUQRXYEW5L4NRN3MDIQKBYM","json":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM.json","graph_json":"https://pith.science/api/pith-number/HYABUQRXYEW5L4NRN3MDIQKBYM/graph.json","events_json":"https://pith.science/api/pith-number/HYABUQRXYEW5L4NRN3MDIQKBYM/events.json","paper":"https://pith.science/paper/HYABUQRX"},"agent_actions":{"view_html":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM","download_json":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM.json","view_paper":"https://pith.science/paper/HYABUQRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12064&json=true","fetch_graph":"https://pith.science/api/pith-number/HYABUQRXYEW5L4NRN3MDIQKBYM/graph.json","fetch_events":"https://pith.science/api/pith-number/HYABUQRXYEW5L4NRN3MDIQKBYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM/action/storage_attestation","attest_author":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM/action/author_attestation","sign_citation":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM/action/citation_signature","submit_replication":"https://pith.science/pith/HYABUQRXYEW5L4NRN3MDIQKBYM/action/replication_record"}},"created_at":"2026-07-05T08:44:59.590089+00:00","updated_at":"2026-07-05T08:44:59.590089+00:00"}