{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A7IP5KAEO56SZMVBUTAIHJTKCH","short_pith_number":"pith:A7IP5KAE","schema_version":"1.0","canonical_sha256":"07d0fea804777d2cb2a1a4c083a66a11da7a182be4bf459abc9eab79618e216d","source":{"kind":"arxiv","id":"2406.05565","version":1},"attestation_state":"computed","paper":{"title":"Medical Vision Generalist: Unifying Medical Imaging Tasks in Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jieru Mei, Junfei Xiao, Sucheng Ren, Xianhang Li, Xiaoke Huang, Yuyin Zhou, Zeyu Wang","submitted_at":"2024-06-08T20:07:39Z","abstract_excerpt":"This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework. Specifically, MVG employs an in-context generation strategy that standardizes the handling of inputs and outputs as images. By treating these tasks as an image generation process conditioned on prompt image-label pairs and input images, this approach enables a flexible unification of various tasks, even those spanning different mod"},"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":"2406.05565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-08T20:07:39Z","cross_cats_sorted":[],"title_canon_sha256":"edeedc517a1af0bc00a3de766ea6ca0b721849dc7e8b7c1159e176d9d25009fc","abstract_canon_sha256":"1b0b081ae2a5a33d604475cfe2ab4e3519c73731f8ac3bd4fceb821d909660d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:29.977981Z","signature_b64":"f4B4F4JjIR+yHAJMtdI4CYeXjbeuaQWy/EtzHyh7UHcPEHD7Simzxem6CfD/0DduQrewq/CuL7ttFeGBkLysDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07d0fea804777d2cb2a1a4c083a66a11da7a182be4bf459abc9eab79618e216d","last_reissued_at":"2026-07-05T08:29:29.977550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:29.977550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Vision Generalist: Unifying Medical Imaging Tasks in Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jieru Mei, Junfei Xiao, Sucheng Ren, Xianhang Li, Xiaoke Huang, Yuyin Zhou, Zeyu Wang","submitted_at":"2024-06-08T20:07:39Z","abstract_excerpt":"This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework. Specifically, MVG employs an in-context generation strategy that standardizes the handling of inputs and outputs as images. By treating these tasks as an image generation process conditioned on prompt image-label pairs and input images, this approach enables a flexible unification of various tasks, even those spanning different mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05565","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/2406.05565/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":"2406.05565","created_at":"2026-07-05T08:29:29.977611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05565v1","created_at":"2026-07-05T08:29:29.977611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05565","created_at":"2026-07-05T08:29:29.977611+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7IP5KAEO56S","created_at":"2026-07-05T08:29:29.977611+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7IP5KAEO56SZMVB","created_at":"2026-07-05T08:29:29.977611+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7IP5KAE","created_at":"2026-07-05T08:29:29.977611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21861","citing_title":"Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06748","citing_title":"From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH","json":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH.json","graph_json":"https://pith.science/api/pith-number/A7IP5KAEO56SZMVBUTAIHJTKCH/graph.json","events_json":"https://pith.science/api/pith-number/A7IP5KAEO56SZMVBUTAIHJTKCH/events.json","paper":"https://pith.science/paper/A7IP5KAE"},"agent_actions":{"view_html":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH","download_json":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH.json","view_paper":"https://pith.science/paper/A7IP5KAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05565&json=true","fetch_graph":"https://pith.science/api/pith-number/A7IP5KAEO56SZMVBUTAIHJTKCH/graph.json","fetch_events":"https://pith.science/api/pith-number/A7IP5KAEO56SZMVBUTAIHJTKCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH/action/storage_attestation","attest_author":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH/action/author_attestation","sign_citation":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH/action/citation_signature","submit_replication":"https://pith.science/pith/A7IP5KAEO56SZMVBUTAIHJTKCH/action/replication_record"}},"created_at":"2026-07-05T08:29:29.977611+00:00","updated_at":"2026-07-05T08:29:29.977611+00:00"}