{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YJCP76HPZILZIL6YJM3YAVKHXR","short_pith_number":"pith:YJCP76HP","schema_version":"1.0","canonical_sha256":"c244fff8efca17942fd84b37805547bc4e9f9fedc0ce7208b2fbe2ae42a13d32","source":{"kind":"arxiv","id":"2311.01092","version":2},"attestation_state":"computed","paper":{"title":"Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Lijian Xu, Shaoting Zhang, Xiaosong Wang, Xinglong Liu, Ziyu Ni","submitted_at":"2023-11-02T08:55:48Z","abstract_excerpt":"The emergence of multi-modal deep learning models has made significant impacts on clinical applications in the last decade. However, the majority of models are limited to single-tasking, without considering disease diagnosis is indeed a multi-task procedure. Here, we demonstrate a unified transformer model specifically designed for multi-modal clinical tasks by incorporating customized instruction tuning. We first compose a multi-task training dataset comprising 13.4 million instruction and ground-truth pairs (with approximately one million radiographs) for the customized tuning, involving bot"},"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":"2311.01092","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T08:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"85b7fc1e6bfcfae76f00b770e088e90226831ca3f5bde8b883ede5999e122b69","abstract_canon_sha256":"c190674f89fa82f4f01403ded99de8ba49e029cb1fee21a95a8f790d0ded2270"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:34.877270Z","signature_b64":"A4oy8UKAFL3gVOznzX9t5O9XHhgt+vEtBxGOgDB0MCHs+9aZGT+l/tVhXpOfZICo07Hn2BIsfrSQCB6FDarbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c244fff8efca17942fd84b37805547bc4e9f9fedc0ce7208b2fbe2ae42a13d32","last_reissued_at":"2026-07-05T07:51:34.876776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:34.876776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Lijian Xu, Shaoting Zhang, Xiaosong Wang, Xinglong Liu, Ziyu Ni","submitted_at":"2023-11-02T08:55:48Z","abstract_excerpt":"The emergence of multi-modal deep learning models has made significant impacts on clinical applications in the last decade. However, the majority of models are limited to single-tasking, without considering disease diagnosis is indeed a multi-task procedure. Here, we demonstrate a unified transformer model specifically designed for multi-modal clinical tasks by incorporating customized instruction tuning. We first compose a multi-task training dataset comprising 13.4 million instruction and ground-truth pairs (with approximately one million radiographs) for the customized tuning, involving bot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01092","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/2311.01092/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":"2311.01092","created_at":"2026-07-05T07:51:34.876829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01092v2","created_at":"2026-07-05T07:51:34.876829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01092","created_at":"2026-07-05T07:51:34.876829+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJCP76HPZILZ","created_at":"2026-07-05T07:51:34.876829+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJCP76HPZILZIL6Y","created_at":"2026-07-05T07:51:34.876829+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJCP76HP","created_at":"2026-07-05T07:51:34.876829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28051","citing_title":"Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02695","citing_title":"XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14316","citing_title":"Seeing Through Experts Eyes A Foundational Vision Language Model Trained on Radiologists Gaze and Reasoning","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR","json":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR.json","graph_json":"https://pith.science/api/pith-number/YJCP76HPZILZIL6YJM3YAVKHXR/graph.json","events_json":"https://pith.science/api/pith-number/YJCP76HPZILZIL6YJM3YAVKHXR/events.json","paper":"https://pith.science/paper/YJCP76HP"},"agent_actions":{"view_html":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR","download_json":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR.json","view_paper":"https://pith.science/paper/YJCP76HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01092&json=true","fetch_graph":"https://pith.science/api/pith-number/YJCP76HPZILZIL6YJM3YAVKHXR/graph.json","fetch_events":"https://pith.science/api/pith-number/YJCP76HPZILZIL6YJM3YAVKHXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR/action/storage_attestation","attest_author":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR/action/author_attestation","sign_citation":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR/action/citation_signature","submit_replication":"https://pith.science/pith/YJCP76HPZILZIL6YJM3YAVKHXR/action/replication_record"}},"created_at":"2026-07-05T07:51:34.876829+00:00","updated_at":"2026-07-05T07:51:34.876829+00:00"}