{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7RJYH7ORBN36ZWMKSW7VMPRX3P","short_pith_number":"pith:7RJYH7OR","schema_version":"1.0","canonical_sha256":"fc5383fdd10b77ecd98a95bf563e37dbf4465a9f7860e5fe54a32c20cd2e8a7f","source":{"kind":"arxiv","id":"2509.00833","version":1},"attestation_state":"computed","paper":{"title":"SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongqiu Wang, Lei Zhu, Sicheng Yang, Sixiang Chen, Zhaohu Xing","submitted_at":"2025-08-31T13:06:37Z","abstract_excerpt":"The DINO family of self-supervised vision models has shown remarkable transferability, yet effectively adapting their representations for segmentation remains challenging. Existing approaches often rely on heavy decoders with multi-scale fusion or complex upsampling, which introduce substantial parameter overhead and computational cost. In this work, we propose SegDINO, an efficient segmentation framework that couples a frozen DINOv3 backbone with a lightweight decoder. SegDINO extracts multi-level features from the pretrained encoder, aligns them to a common resolution and channel width, and "},"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":"2509.00833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T13:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"b6588ef8d4ca4caa4997468f2718c58a6c404c3830c34f09f75fb848d6dc8667","abstract_canon_sha256":"8a130691ea547724ddb4240850aa67cc99ff04a9f2896150777a17fcf5d85b55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:23.395847Z","signature_b64":"vtF28ilKqFsUQetaXRKsNnU/2dL0AD2kIkKt2UH8abqHTmh0PIwuecGUT1C+f113UzRIjJmtteURVZ1fC+ahAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc5383fdd10b77ecd98a95bf563e37dbf4465a9f7860e5fe54a32c20cd2e8a7f","last_reissued_at":"2026-07-05T12:02:23.395205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:23.395205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongqiu Wang, Lei Zhu, Sicheng Yang, Sixiang Chen, Zhaohu Xing","submitted_at":"2025-08-31T13:06:37Z","abstract_excerpt":"The DINO family of self-supervised vision models has shown remarkable transferability, yet effectively adapting their representations for segmentation remains challenging. Existing approaches often rely on heavy decoders with multi-scale fusion or complex upsampling, which introduce substantial parameter overhead and computational cost. In this work, we propose SegDINO, an efficient segmentation framework that couples a frozen DINOv3 backbone with a lightweight decoder. SegDINO extracts multi-level features from the pretrained encoder, aligns them to a common resolution and channel width, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00833","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/2509.00833/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":"2509.00833","created_at":"2026-07-05T12:02:23.395293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00833v1","created_at":"2026-07-05T12:02:23.395293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00833","created_at":"2026-07-05T12:02:23.395293+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RJYH7ORBN36","created_at":"2026-07-05T12:02:23.395293+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RJYH7ORBN36ZWMK","created_at":"2026-07-05T12:02:23.395293+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RJYH7OR","created_at":"2026-07-05T12:02:23.395293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18886","citing_title":"DINO-Med3D: Bridging Dimension and Domain Gaps in Volumetric Segmentation via Progressive Adaptation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17989","citing_title":"Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04888","citing_title":"HD-DinoMoE: A Class-Aware Hierarchical Dual Mixture-of-Experts Network for Scleral Anomaly Segmentation in Complex Acquisition Scenarios","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27444","citing_title":"SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23033","citing_title":"Uncovering the Latent Potential of Deep Intermediate Representations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07191","citing_title":"Resolution scaling governs DINOv3 transfer performance in chest radiograph classification","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P","json":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P.json","graph_json":"https://pith.science/api/pith-number/7RJYH7ORBN36ZWMKSW7VMPRX3P/graph.json","events_json":"https://pith.science/api/pith-number/7RJYH7ORBN36ZWMKSW7VMPRX3P/events.json","paper":"https://pith.science/paper/7RJYH7OR"},"agent_actions":{"view_html":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P","download_json":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P.json","view_paper":"https://pith.science/paper/7RJYH7OR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00833&json=true","fetch_graph":"https://pith.science/api/pith-number/7RJYH7ORBN36ZWMKSW7VMPRX3P/graph.json","fetch_events":"https://pith.science/api/pith-number/7RJYH7ORBN36ZWMKSW7VMPRX3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P/action/storage_attestation","attest_author":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P/action/author_attestation","sign_citation":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P/action/citation_signature","submit_replication":"https://pith.science/pith/7RJYH7ORBN36ZWMKSW7VMPRX3P/action/replication_record"}},"created_at":"2026-07-05T12:02:23.395293+00:00","updated_at":"2026-07-05T12:02:23.395293+00:00"}