{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F7XW7ZQ657NWWGXNHHHTWZ52Y7","short_pith_number":"pith:F7XW7ZQ6","schema_version":"1.0","canonical_sha256":"2fef6fe61eefdb6b1aed39cf3b67bac7d6b4c6a88f962507fe1bbedcb4bba6da","source":{"kind":"arxiv","id":"2608.10635","version":1},"attestation_state":"computed","paper":{"title":"MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hualiang Wang, Jiaming Lin, Jian Wu, Shujian Gao, Siming Fu, Songtao Jiang, Yixin Chen, Yuan Wang, Zuozhu Liu","submitted_at":"2026-08-11T08:22:13Z","abstract_excerpt":"Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging. Existing approaches either verbalize regions as coordinate strings or rely on external modules that decouple perception from understanding, creating representation gaps for region-language alignment. We present MedUP, a Med-VLM that natively unifies perception and understanding within a shared token space. At its core lies UniMedTok, a region tokenizer that encodes masks as discrete tokens in the LLM vocabulary, enabling the model to seam"},"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":"2608.10635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T08:22:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1a94033454b56ec7b63e1745483f1f451d7b55a2a9900411d17459102cfb9a2","abstract_canon_sha256":"466d771133a10293672e7b143e5bac79aad2394febf27cf1fb6d68e61fa1be74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:55.118697Z","signature_b64":"XCACPBOe/C1+JPJGn/wAUvBcdjl+aVOjdxnurXkHlkbkv+I5W4/WlMrCSfbNn+eqtggeC3eL7REmJor1/kPlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fef6fe61eefdb6b1aed39cf3b67bac7d6b4c6a88f962507fe1bbedcb4bba6da","last_reissued_at":"2026-08-12T01:22:55.117123Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:55.117123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hualiang Wang, Jiaming Lin, Jian Wu, Shujian Gao, Siming Fu, Songtao Jiang, Yixin Chen, Yuan Wang, Zuozhu Liu","submitted_at":"2026-08-11T08:22:13Z","abstract_excerpt":"Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging. Existing approaches either verbalize regions as coordinate strings or rely on external modules that decouple perception from understanding, creating representation gaps for region-language alignment. We present MedUP, a Med-VLM that natively unifies perception and understanding within a shared token space. At its core lies UniMedTok, a region tokenizer that encodes masks as discrete tokens in the LLM vocabulary, enabling the model to seam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10635","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/2608.10635/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":"2608.10635","created_at":"2026-08-12T01:22:55.120896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10635v1","created_at":"2026-08-12T01:22:55.120896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10635","created_at":"2026-08-12T01:22:55.120896+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7XW7ZQ657NW","created_at":"2026-08-12T01:22:55.120896+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7XW7ZQ657NWWGXN","created_at":"2026-08-12T01:22:55.120896+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7XW7ZQ6","created_at":"2026-08-12T01:22:55.120896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7","json":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7.json","graph_json":"https://pith.science/api/pith-number/F7XW7ZQ657NWWGXNHHHTWZ52Y7/graph.json","events_json":"https://pith.science/api/pith-number/F7XW7ZQ657NWWGXNHHHTWZ52Y7/events.json","paper":"https://pith.science/paper/F7XW7ZQ6"},"agent_actions":{"view_html":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7","download_json":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7.json","view_paper":"https://pith.science/paper/F7XW7ZQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10635&json=true","fetch_graph":"https://pith.science/api/pith-number/F7XW7ZQ657NWWGXNHHHTWZ52Y7/graph.json","fetch_events":"https://pith.science/api/pith-number/F7XW7ZQ657NWWGXNHHHTWZ52Y7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7/action/storage_attestation","attest_author":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7/action/author_attestation","sign_citation":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7/action/citation_signature","submit_replication":"https://pith.science/pith/F7XW7ZQ657NWWGXNHHHTWZ52Y7/action/replication_record"}},"created_at":"2026-08-12T01:22:55.120896+00:00","updated_at":"2026-08-12T01:22:55.120896+00:00"}