{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZQFA4EX2BQNAWP4JJDKU3UNK2H","short_pith_number":"pith:ZQFA4EX2","schema_version":"1.0","canonical_sha256":"cc0a0e12fa0c1a0b3f8948d54dd1aad1deef7678fb06477ab45cbaa06ecf20c5","source":{"kind":"arxiv","id":"2412.13558","version":1},"attestation_state":"computed","paper":{"title":"Read Like a Radiologist: Efficient Vision-Language Model for 3D Medical Imaging Interpretation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Changsun Lee, Cheong-Il Shin, Hyun Jeong Park, Jeong Eun Lee, Jong Chul Ye, Sangjoon Park, Woo Hee Choi","submitted_at":"2024-12-18T07:19:48Z","abstract_excerpt":"Recent medical vision-language models (VLMs) have shown promise in 2D medical image interpretation. However extending them to 3D medical imaging has been challenging due to computational complexities and data scarcity. Although a few recent VLMs specified for 3D medical imaging have emerged, all are limited to learning volumetric representation of a 3D medical image as a set of sub-volumetric features. Such process introduces overly correlated representations along the z-axis that neglect slice-specific clinical details, particularly for 3D medical images where adjacent slices have low redunda"},"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":"2412.13558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2024-12-18T07:19:48Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"b37453458347b0179c5fd6fcf75bccaa0bc33d0744ced5ffa612dd649843901b","abstract_canon_sha256":"50a6d474af8f64d309109aefdaeeb20f40e4a9378c16f95dce96b761c5ad11de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:03.970634Z","signature_b64":"+SkrpX13HPln3sKfOMUrV6feRYjtsi8VV/AqYcIwYGPwMVE418aLjZ5xuNJpXi5ZJAn6r/Rb/j7N3GDZm51DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc0a0e12fa0c1a0b3f8948d54dd1aad1deef7678fb06477ab45cbaa06ecf20c5","last_reissued_at":"2026-07-05T09:51:03.970135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:03.970135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Read Like a Radiologist: Efficient Vision-Language Model for 3D Medical Imaging Interpretation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Changsun Lee, Cheong-Il Shin, Hyun Jeong Park, Jeong Eun Lee, Jong Chul Ye, Sangjoon Park, Woo Hee Choi","submitted_at":"2024-12-18T07:19:48Z","abstract_excerpt":"Recent medical vision-language models (VLMs) have shown promise in 2D medical image interpretation. However extending them to 3D medical imaging has been challenging due to computational complexities and data scarcity. Although a few recent VLMs specified for 3D medical imaging have emerged, all are limited to learning volumetric representation of a 3D medical image as a set of sub-volumetric features. Such process introduces overly correlated representations along the z-axis that neglect slice-specific clinical details, particularly for 3D medical images where adjacent slices have low redunda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13558","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/2412.13558/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":"2412.13558","created_at":"2026-07-05T09:51:03.970189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13558v1","created_at":"2026-07-05T09:51:03.970189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13558","created_at":"2026-07-05T09:51:03.970189+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQFA4EX2BQNA","created_at":"2026-07-05T09:51:03.970189+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQFA4EX2BQNAWP4J","created_at":"2026-07-05T09:51:03.970189+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQFA4EX2","created_at":"2026-07-05T09:51:03.970189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08787","citing_title":"Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20277","citing_title":"Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08787","citing_title":"Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10437","citing_title":"Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H","json":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H.json","graph_json":"https://pith.science/api/pith-number/ZQFA4EX2BQNAWP4JJDKU3UNK2H/graph.json","events_json":"https://pith.science/api/pith-number/ZQFA4EX2BQNAWP4JJDKU3UNK2H/events.json","paper":"https://pith.science/paper/ZQFA4EX2"},"agent_actions":{"view_html":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H","download_json":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H.json","view_paper":"https://pith.science/paper/ZQFA4EX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13558&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQFA4EX2BQNAWP4JJDKU3UNK2H/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQFA4EX2BQNAWP4JJDKU3UNK2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H/action/storage_attestation","attest_author":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H/action/author_attestation","sign_citation":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H/action/citation_signature","submit_replication":"https://pith.science/pith/ZQFA4EX2BQNAWP4JJDKU3UNK2H/action/replication_record"}},"created_at":"2026-07-05T09:51:03.970189+00:00","updated_at":"2026-07-05T09:51:03.970189+00:00"}