{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R4N2FOWY2XSVGXVS6TDTTA5I2D","short_pith_number":"pith:R4N2FOWY","schema_version":"1.0","canonical_sha256":"8f1ba2bad8d5e5535eb2f4c73983a8d0eb5c9fd1c7b0ee3baa4ffa2b228a7947","source":{"kind":"arxiv","id":"2404.10237","version":3},"attestation_state":"computed","paper":{"title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Li Yuan, Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Zuozhu Liu","submitted_at":"2024-04-16T02:35:17Z","abstract_excerpt":"Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks, and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing, hindering their clinical utility across diverse resource-constrained scenarios in practice. In this paper, we propose a novel and lightweight framework Med-MoE (Mixture-of-Experts) that tackles both discriminative and generative multimodal medi"},"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":"2404.10237","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T02:35:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6f33123d0db713dbc1d4cf10664d3fa7f79cf0e0e28b2fa597e23286240dc871","abstract_canon_sha256":"0a67604b0359426b8edeb7e1604492f1dbfb24212d714e73982013396f8ec3b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:32.532505Z","signature_b64":"eyS1c1PEoDVGOm43stTc24cXapZQXJDPph/KdBIbxjn8K6jZ2pq/Bup1mrseN4XZFlPyMNOVB17zUM4JqKvPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1ba2bad8d5e5535eb2f4c73983a8d0eb5c9fd1c7b0ee3baa4ffa2b228a7947","last_reissued_at":"2026-07-05T09:01:32.532013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:32.532013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Li Yuan, Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Zuozhu Liu","submitted_at":"2024-04-16T02:35:17Z","abstract_excerpt":"Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks, and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing, hindering their clinical utility across diverse resource-constrained scenarios in practice. In this paper, we propose a novel and lightweight framework Med-MoE (Mixture-of-Experts) that tackles both discriminative and generative multimodal medi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10237","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/2404.10237/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":"2404.10237","created_at":"2026-07-05T09:01:32.532069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10237v3","created_at":"2026-07-05T09:01:32.532069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10237","created_at":"2026-07-05T09:01:32.532069+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4N2FOWY2XSV","created_at":"2026-07-05T09:01:32.532069+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4N2FOWY2XSVGXVS","created_at":"2026-07-05T09:01:32.532069+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4N2FOWY","created_at":"2026-07-05T09:01:32.532069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27431","citing_title":"Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25518","citing_title":"Cross-Stage Attention Multi-Expert Network for Radiologist-Inspired Breast Ultrasound Diagnosis","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05831","citing_title":"HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07361","citing_title":"BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10233","citing_title":"Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D","json":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D.json","graph_json":"https://pith.science/api/pith-number/R4N2FOWY2XSVGXVS6TDTTA5I2D/graph.json","events_json":"https://pith.science/api/pith-number/R4N2FOWY2XSVGXVS6TDTTA5I2D/events.json","paper":"https://pith.science/paper/R4N2FOWY"},"agent_actions":{"view_html":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D","download_json":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D.json","view_paper":"https://pith.science/paper/R4N2FOWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10237&json=true","fetch_graph":"https://pith.science/api/pith-number/R4N2FOWY2XSVGXVS6TDTTA5I2D/graph.json","fetch_events":"https://pith.science/api/pith-number/R4N2FOWY2XSVGXVS6TDTTA5I2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D/action/storage_attestation","attest_author":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D/action/author_attestation","sign_citation":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D/action/citation_signature","submit_replication":"https://pith.science/pith/R4N2FOWY2XSVGXVS6TDTTA5I2D/action/replication_record"}},"created_at":"2026-07-05T09:01:32.532069+00:00","updated_at":"2026-07-05T09:01:32.532069+00:00"}