{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3WZWEHSMNKUSI7B2NOSQTTXD3V","short_pith_number":"pith:3WZWEHSM","schema_version":"1.0","canonical_sha256":"ddb3621e4c6aa9247c3a6ba509cee3dd7335cbc630aac5a64eeecc686c1ba9ba","source":{"kind":"arxiv","id":"2409.17508","version":2},"attestation_state":"computed","paper":{"title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fanbin Mo, Ji Wu, Miao Li, Xun Zhu, Ying Hu","submitted_at":"2024-09-26T03:33:26Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have shown impressive capabilities as a general-purpose interface for various visual and linguistic tasks. However, building a unified MLLM for multi-task learning in the medical field remains a thorny challenge. To mitigate the tug-of-war problem of multi-modal multi-task optimization in MLLMs, recent advances primarily focus on improving the LLM components, while neglecting the connector that bridges the gap between modalities. In this paper, we introduce Uni-Med, a novel medical generalist foundation model which consists of a universal visual featur"},"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":"2409.17508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T03:33:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"73a399cb4675596557c6a031832495f167fd6332320d399b099dafe7f07b8b56","abstract_canon_sha256":"3bd496ad0180a3d23cf2bc882e7bc5da858a172874c10b1155e02e0f18ff8eda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:33.623889Z","signature_b64":"WF51gFYxS1eKFvvAMLYk44cGWYBVUG6SNKHbaOtYGzIlLhJ3LDJE3Ht27n7LnhA8ShiHVOe5U7eTrABtIcNzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddb3621e4c6aa9247c3a6ba509cee3dd7335cbc630aac5a64eeecc686c1ba9ba","last_reissued_at":"2026-07-05T09:29:33.623395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:33.623395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fanbin Mo, Ji Wu, Miao Li, Xun Zhu, Ying Hu","submitted_at":"2024-09-26T03:33:26Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have shown impressive capabilities as a general-purpose interface for various visual and linguistic tasks. However, building a unified MLLM for multi-task learning in the medical field remains a thorny challenge. To mitigate the tug-of-war problem of multi-modal multi-task optimization in MLLMs, recent advances primarily focus on improving the LLM components, while neglecting the connector that bridges the gap between modalities. In this paper, we introduce Uni-Med, a novel medical generalist foundation model which consists of a universal visual featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17508","kind":"arxiv","version":2},"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/2409.17508/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":"2409.17508","created_at":"2026-07-05T09:29:33.623450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17508v2","created_at":"2026-07-05T09:29:33.623450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17508","created_at":"2026-07-05T09:29:33.623450+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WZWEHSMNKUS","created_at":"2026-07-05T09:29:33.623450+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WZWEHSMNKUSI7B2","created_at":"2026-07-05T09:29:33.623450+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WZWEHSM","created_at":"2026-07-05T09:29:33.623450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21393","citing_title":"TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V","json":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V.json","graph_json":"https://pith.science/api/pith-number/3WZWEHSMNKUSI7B2NOSQTTXD3V/graph.json","events_json":"https://pith.science/api/pith-number/3WZWEHSMNKUSI7B2NOSQTTXD3V/events.json","paper":"https://pith.science/paper/3WZWEHSM"},"agent_actions":{"view_html":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V","download_json":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V.json","view_paper":"https://pith.science/paper/3WZWEHSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17508&json=true","fetch_graph":"https://pith.science/api/pith-number/3WZWEHSMNKUSI7B2NOSQTTXD3V/graph.json","fetch_events":"https://pith.science/api/pith-number/3WZWEHSMNKUSI7B2NOSQTTXD3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V/action/storage_attestation","attest_author":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V/action/author_attestation","sign_citation":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V/action/citation_signature","submit_replication":"https://pith.science/pith/3WZWEHSMNKUSI7B2NOSQTTXD3V/action/replication_record"}},"created_at":"2026-07-05T09:29:33.623450+00:00","updated_at":"2026-07-05T09:29:33.623450+00:00"}