{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXJWYKHCF76EM3CJWTJJVEEKW6","short_pith_number":"pith:MXJWYKHC","schema_version":"1.0","canonical_sha256":"65d36c28e22ffc466c49b4d29a908ab7a55931f6322b44742e64df56ee22adeb","source":{"kind":"arxiv","id":"2504.01792","version":2},"attestation_state":"computed","paper":{"title":"UniViTAR: Unified Vision Transformer with Native Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bairui Wang, Jie Qin, Limeng Qiao, Lin Ma, Shuang Xu, Siqi Yang, Yiyang Gan","submitted_at":"2025-04-02T14:59:39Z","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"},"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":"2504.01792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T14:59:39Z","cross_cats_sorted":[],"title_canon_sha256":"87a43ed36f7360a22baaaf43057ed011aeac28c262a4709b4a0e294e44ae18cf","abstract_canon_sha256":"54d223299da04be13aca28cbe79d434f4e10841973fe4dbf46d6f0adaa1a4f6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:43.666034Z","signature_b64":"IfyaAeMUFkGdP65rRVpIMRlc67FMBm8+b6M81thhdglmw61M9/EuJ6qXaPeMEXEdkas4O3AAL+VEzo9w/0n9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d36c28e22ffc466c49b4d29a908ab7a55931f6322b44742e64df56ee22adeb","last_reissued_at":"2026-07-05T11:11:43.665555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:43.665555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniViTAR: Unified Vision Transformer with Native Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bairui Wang, Jie Qin, Limeng Qiao, Lin Ma, Shuang Xu, Siqi Yang, Yiyang Gan","submitted_at":"2025-04-02T14:59:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01792","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/2504.01792/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":"2504.01792","created_at":"2026-07-05T11:11:43.665609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01792v2","created_at":"2026-07-05T11:11:43.665609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01792","created_at":"2026-07-05T11:11:43.665609+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXJWYKHCF76E","created_at":"2026-07-05T11:11:43.665609+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXJWYKHCF76EM3CJ","created_at":"2026-07-05T11:11:43.665609+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXJWYKHC","created_at":"2026-07-05T11:11:43.665609+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/MXJWYKHCF76EM3CJWTJJVEEKW6","json":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6.json","graph_json":"https://pith.science/api/pith-number/MXJWYKHCF76EM3CJWTJJVEEKW6/graph.json","events_json":"https://pith.science/api/pith-number/MXJWYKHCF76EM3CJWTJJVEEKW6/events.json","paper":"https://pith.science/paper/MXJWYKHC"},"agent_actions":{"view_html":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6","download_json":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6.json","view_paper":"https://pith.science/paper/MXJWYKHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01792&json=true","fetch_graph":"https://pith.science/api/pith-number/MXJWYKHCF76EM3CJWTJJVEEKW6/graph.json","fetch_events":"https://pith.science/api/pith-number/MXJWYKHCF76EM3CJWTJJVEEKW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6/action/storage_attestation","attest_author":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6/action/author_attestation","sign_citation":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6/action/citation_signature","submit_replication":"https://pith.science/pith/MXJWYKHCF76EM3CJWTJJVEEKW6/action/replication_record"}},"created_at":"2026-07-05T11:11:43.665609+00:00","updated_at":"2026-07-05T11:11:43.665609+00:00"}