{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MXJWYKHCF76EM3CJWTJJVEEKW6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"54d223299da04be13aca28cbe79d434f4e10841973fe4dbf46d6f0adaa1a4f6b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T14:59:39Z","title_canon_sha256":"87a43ed36f7360a22baaaf43057ed011aeac28c262a4709b4a0e294e44ae18cf"},"schema_version":"1.0","source":{"id":"2504.01792","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01792","created_at":"2026-07-05T11:11:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01792v2","created_at":"2026-07-05T11:11:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01792","created_at":"2026-07-05T11:11:43Z"},{"alias_kind":"pith_short_12","alias_value":"MXJWYKHCF76E","created_at":"2026-07-05T11:11:43Z"},{"alias_kind":"pith_short_16","alias_value":"MXJWYKHCF76EM3CJ","created_at":"2026-07-05T11:11:43Z"},{"alias_kind":"pith_short_8","alias_value":"MXJWYKHC","created_at":"2026-07-05T11:11:43Z"}],"graph_snapshots":[{"event_id":"sha256:43292d80fa85a403ca4ecb6d5737d97f275a1fb107b44fd692584316d20e6e4f","target":"graph","created_at":"2026-07-05T11:11:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.01792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional Vision Transformer simplifies visual modeling by standardizing input resolutions, often disregarding the variability of natural visual data and compromising spatial-contextual fidelity. While preliminary explorations have superficially investigated native resolution modeling, existing approaches still lack systematic analysis from a visual representation perspective. To bridge this gap, we introduce UniViTAR, a family of homogeneous vision foundation models tailored for unified visual modality and native resolution scenario in the era of multimodal. Our framework first conducts ar","authors_text":"Bairui Wang, Jie Qin, Limeng Qiao, Lin Ma, Shuang Xu, Siqi Yang, Yiyang Gan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T14:59:39Z","title":"UniViTAR: Unified Vision Transformer with Native Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01792","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:44dd73e85c7a897e2c0686180d2b7ead5494510451cac4750764489539ff5a0d","target":"record","created_at":"2026-07-05T11:11:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"54d223299da04be13aca28cbe79d434f4e10841973fe4dbf46d6f0adaa1a4f6b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T14:59:39Z","title_canon_sha256":"87a43ed36f7360a22baaaf43057ed011aeac28c262a4709b4a0e294e44ae18cf"},"schema_version":"1.0","source":{"id":"2504.01792","kind":"arxiv","version":2}},"canonical_sha256":"65d36c28e22ffc466c49b4d29a908ab7a55931f6322b44742e64df56ee22adeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65d36c28e22ffc466c49b4d29a908ab7a55931f6322b44742e64df56ee22adeb","first_computed_at":"2026-07-05T11:11:43.665555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:43.665555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IfyaAeMUFkGdP65rRVpIMRlc67FMBm8+b6M81thhdglmw61M9/EuJ6qXaPeMEXEdkas4O3AAL+VEzo9w/0n9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:43.666034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01792","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44dd73e85c7a897e2c0686180d2b7ead5494510451cac4750764489539ff5a0d","sha256:43292d80fa85a403ca4ecb6d5737d97f275a1fb107b44fd692584316d20e6e4f"],"state_sha256":"35fc7405ab1cdb115f08a1005f9606ef9bf2c97f9c3332271b50f2b472c4d6cb"}