{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VISWB2E42PS4YW3CYRXFSMQQR5","short_pith_number":"pith:VISWB2E4","schema_version":"1.0","canonical_sha256":"aa2560e89cd3e5cc5b62c46e5932108f73bcb06d5fc0ac965e369b1ea8e6a9df","source":{"kind":"arxiv","id":"2310.18341","version":3},"attestation_state":"computed","paper":{"title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyungjin Kim, Jiwon Youn, Mansu Kim, Seowoo Lee, Soon Ho Yoon","submitted_at":"2023-10-22T06:22:37Z","abstract_excerpt":"Purpose: This study aimed to develop an open-source multimodal large language model (CXR-LLAVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists Materials and Methods: For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset 2). After pre-training a vision transformer with Dataset 1, we integrated it with an LLM influenced by"},"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":"2310.18341","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T06:22:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ca3e02a940ab880e63fd0c05c66b4993132927a061fde7c357c0e439b4d7839","abstract_canon_sha256":"acdaa69fee6064dc2a70980b1c865e039bfc5f4f42e5ee3d69e4506d97f42a64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:21.380818Z","signature_b64":"p12TUTkIg0+j2fTP9aBckrjU96y29GucS53oCnHXoFy2PDbId7QIQXt7dsGcVpXCACK3gYiZ0g3Nf0zgkGoKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa2560e89cd3e5cc5b62c46e5932108f73bcb06d5fc0ac965e369b1ea8e6a9df","last_reissued_at":"2026-07-05T07:33:21.380393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:21.380393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyungjin Kim, Jiwon Youn, Mansu Kim, Seowoo Lee, Soon Ho Yoon","submitted_at":"2023-10-22T06:22:37Z","abstract_excerpt":"Purpose: This study aimed to develop an open-source multimodal large language model (CXR-LLAVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists Materials and Methods: For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset 2). After pre-training a vision transformer with Dataset 1, we integrated it with an LLM influenced by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18341","kind":"arxiv","version":3},"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/2310.18341/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":"2310.18341","created_at":"2026-07-05T07:33:21.380444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18341v3","created_at":"2026-07-05T07:33:21.380444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18341","created_at":"2026-07-05T07:33:21.380444+00:00"},{"alias_kind":"pith_short_12","alias_value":"VISWB2E42PS4","created_at":"2026-07-05T07:33:21.380444+00:00"},{"alias_kind":"pith_short_16","alias_value":"VISWB2E42PS4YW3C","created_at":"2026-07-05T07:33:21.380444+00:00"},{"alias_kind":"pith_short_8","alias_value":"VISWB2E4","created_at":"2026-07-05T07:33:21.380444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09097","citing_title":"RadEyeVideo: Enhancing general-domain Large Vision Language Model for chest X-ray analysis with video representations of eye gaze","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5","json":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5.json","graph_json":"https://pith.science/api/pith-number/VISWB2E42PS4YW3CYRXFSMQQR5/graph.json","events_json":"https://pith.science/api/pith-number/VISWB2E42PS4YW3CYRXFSMQQR5/events.json","paper":"https://pith.science/paper/VISWB2E4"},"agent_actions":{"view_html":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5","download_json":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5.json","view_paper":"https://pith.science/paper/VISWB2E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18341&json=true","fetch_graph":"https://pith.science/api/pith-number/VISWB2E42PS4YW3CYRXFSMQQR5/graph.json","fetch_events":"https://pith.science/api/pith-number/VISWB2E42PS4YW3CYRXFSMQQR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5/action/storage_attestation","attest_author":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5/action/author_attestation","sign_citation":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5/action/citation_signature","submit_replication":"https://pith.science/pith/VISWB2E42PS4YW3CYRXFSMQQR5/action/replication_record"}},"created_at":"2026-07-05T07:33:21.380444+00:00","updated_at":"2026-07-05T07:33:21.380444+00:00"}