{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T2Q4MNJ4ENVVCT5PRYJPSMHSNT","short_pith_number":"pith:T2Q4MNJ4","schema_version":"1.0","canonical_sha256":"9ea1c6353c236b514faf8e12f930f26cd781ade65af98ed8c8ed3f9083764cd9","source":{"kind":"arxiv","id":"2401.02797","version":3},"attestation_state":"computed","paper":{"title":"PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gang Liu, Genrong He, Jinlong He, Pengfei Li, Shenjun Zhong, Zhaolin Chen","submitted_at":"2024-01-05T13:22:12Z","abstract_excerpt":"Multimodal large language models (MLLMs) represent an evolutionary expansion in the capabilities of traditional large language models, enabling them to tackle challenges that surpass the scope of purely text-based applications. It leverages the knowledge previously encoded within these language models, thereby enhancing their applicability and functionality in the reign of multimodal contexts. Recent works investigate the adaptation of MLLMs as a universal solution to address medical multi-modal problems as a generative task. In this paper, we propose a parameter efficient framework for fine-t"},"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":"2401.02797","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-05T13:22:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0d36f657a2ef32df6c21d69ca6e0b90f8256ad992d036e220d86c1fbb22a739","abstract_canon_sha256":"28c045a123bf848fb0afe7e78b6d1946d96de3a23acd39f3e6a5e8f6c8d00e89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:31.848477Z","signature_b64":"vlHX5sR/0ry6ypTnxyowCrj+ysOMSDN6+zeGHtmVT5HUJTWFeFn8tdFCqUe6bpQJ4xPXstIsVnVUedQOCcW1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea1c6353c236b514faf8e12f930f26cd781ade65af98ed8c8ed3f9083764cd9","last_reissued_at":"2026-07-05T10:01:31.847996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:31.847996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gang Liu, Genrong He, Jinlong He, Pengfei Li, Shenjun Zhong, Zhaolin Chen","submitted_at":"2024-01-05T13:22:12Z","abstract_excerpt":"Multimodal large language models (MLLMs) represent an evolutionary expansion in the capabilities of traditional large language models, enabling them to tackle challenges that surpass the scope of purely text-based applications. It leverages the knowledge previously encoded within these language models, thereby enhancing their applicability and functionality in the reign of multimodal contexts. Recent works investigate the adaptation of MLLMs as a universal solution to address medical multi-modal problems as a generative task. In this paper, we propose a parameter efficient framework for fine-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02797","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/2401.02797/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":"2401.02797","created_at":"2026-07-05T10:01:31.848049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02797v3","created_at":"2026-07-05T10:01:31.848049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02797","created_at":"2026-07-05T10:01:31.848049+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2Q4MNJ4ENVV","created_at":"2026-07-05T10:01:31.848049+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2Q4MNJ4ENVVCT5P","created_at":"2026-07-05T10:01:31.848049+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2Q4MNJ4","created_at":"2026-07-05T10:01:31.848049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05535","citing_title":"Noise-Aware Visual Representation Learning for Medical Visual Question Answering","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24159","citing_title":"EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04509","citing_title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06173","citing_title":"Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06173","citing_title":"Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT","json":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT.json","graph_json":"https://pith.science/api/pith-number/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/graph.json","events_json":"https://pith.science/api/pith-number/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/events.json","paper":"https://pith.science/paper/T2Q4MNJ4"},"agent_actions":{"view_html":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT","download_json":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT.json","view_paper":"https://pith.science/paper/T2Q4MNJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02797&json=true","fetch_graph":"https://pith.science/api/pith-number/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/graph.json","fetch_events":"https://pith.science/api/pith-number/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/action/storage_attestation","attest_author":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/action/author_attestation","sign_citation":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/action/citation_signature","submit_replication":"https://pith.science/pith/T2Q4MNJ4ENVVCT5PRYJPSMHSNT/action/replication_record"}},"created_at":"2026-07-05T10:01:31.848049+00:00","updated_at":"2026-07-05T10:01:31.848049+00:00"}