{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4W6J6APYXPRSPOZ5PTEQSCUJJB","short_pith_number":"pith:4W6J6APY","schema_version":"1.0","canonical_sha256":"e5bc9f01f8bbe327bb3d7cc9090a89487e15d4712d03ec57911c0a3e413a0871","source":{"kind":"arxiv","id":"2506.15477","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Large Language Models for Medical Report Generation via Customized Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunlei Li, Jingliang Hu, Jingyang Hou, Lichao Mou, Xiao Xiang Zhu, Yilei Shi","submitted_at":"2025-06-18T14:09:34Z","abstract_excerpt":"Medical report generation from imaging data remains a challenging task in clinical practice. While large language models (LLMs) show great promise in addressing this challenge, their effective integration with medical imaging data still deserves in-depth exploration. In this paper, we present MRG-LLM, a novel multimodal large language model (MLLM) that combines a frozen LLM with a learnable visual encoder and introduces a dynamic prompt customization mechanism. Our key innovation lies in generating instance-specific prompts tailored to individual medical images through conditional affine trans"},"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":"2506.15477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-18T14:09:34Z","cross_cats_sorted":[],"title_canon_sha256":"ed4ab0e42942622d68d9f539448b56408b1924182d3c8a8d126bb0c111b3a01b","abstract_canon_sha256":"cc204145ab5b651ea1251c5a381027830074b8cfc72ba1362a162ca59ede3edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:44.419605Z","signature_b64":"wDkghyD0XpDXnxpgduTYPymWURWvZAJ6EPD9fnFbyL9EeCDWvt3OLk+D71/lPiGi38RjzTunt9n2iYV71auwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5bc9f01f8bbe327bb3d7cc9090a89487e15d4712d03ec57911c0a3e413a0871","last_reissued_at":"2026-07-05T11:23:44.419092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:44.419092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Large Language Models for Medical Report Generation via Customized Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunlei Li, Jingliang Hu, Jingyang Hou, Lichao Mou, Xiao Xiang Zhu, Yilei Shi","submitted_at":"2025-06-18T14:09:34Z","abstract_excerpt":"Medical report generation from imaging data remains a challenging task in clinical practice. While large language models (LLMs) show great promise in addressing this challenge, their effective integration with medical imaging data still deserves in-depth exploration. In this paper, we present MRG-LLM, a novel multimodal large language model (MLLM) that combines a frozen LLM with a learnable visual encoder and introduces a dynamic prompt customization mechanism. Our key innovation lies in generating instance-specific prompts tailored to individual medical images through conditional affine trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15477","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/2506.15477/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":"2506.15477","created_at":"2026-07-05T11:23:44.419153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15477v1","created_at":"2026-07-05T11:23:44.419153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15477","created_at":"2026-07-05T11:23:44.419153+00:00"},{"alias_kind":"pith_short_12","alias_value":"4W6J6APYXPRS","created_at":"2026-07-05T11:23:44.419153+00:00"},{"alias_kind":"pith_short_16","alias_value":"4W6J6APYXPRSPOZ5","created_at":"2026-07-05T11:23:44.419153+00:00"},{"alias_kind":"pith_short_8","alias_value":"4W6J6APY","created_at":"2026-07-05T11:23:44.419153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01908","citing_title":"Towards Real-World Ultrasound Understanding: Large Vision-Language Models from Multi-Image Examinations with Long-Form Reports","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01756","citing_title":"NeuroSymb-MRG: Differentiable Abductive Reasoning with Active Uncertainty Minimization for Radiology Report Generation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB","json":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB.json","graph_json":"https://pith.science/api/pith-number/4W6J6APYXPRSPOZ5PTEQSCUJJB/graph.json","events_json":"https://pith.science/api/pith-number/4W6J6APYXPRSPOZ5PTEQSCUJJB/events.json","paper":"https://pith.science/paper/4W6J6APY"},"agent_actions":{"view_html":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB","download_json":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB.json","view_paper":"https://pith.science/paper/4W6J6APY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15477&json=true","fetch_graph":"https://pith.science/api/pith-number/4W6J6APYXPRSPOZ5PTEQSCUJJB/graph.json","fetch_events":"https://pith.science/api/pith-number/4W6J6APYXPRSPOZ5PTEQSCUJJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB/action/storage_attestation","attest_author":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB/action/author_attestation","sign_citation":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB/action/citation_signature","submit_replication":"https://pith.science/pith/4W6J6APYXPRSPOZ5PTEQSCUJJB/action/replication_record"}},"created_at":"2026-07-05T11:23:44.419153+00:00","updated_at":"2026-07-05T11:23:44.419153+00:00"}