{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QDA35CBLT6FFLV5SEBAGQQYSMN","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":"c23633c4bdce9845632498448eb56b4678c69ab902f0302ee1bd7159dbd3b461","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T08:53:13Z","title_canon_sha256":"d7a37d041710c66e387d16eea886195e78de5b41d2c5b1352c9c13645ee1fa98"},"schema_version":"1.0","source":{"id":"2403.18361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18361","created_at":"2026-07-05T08:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18361v2","created_at":"2026-07-05T08:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18361","created_at":"2026-07-05T08:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"QDA35CBLT6FF","created_at":"2026-07-05T08:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"QDA35CBLT6FFLV5S","created_at":"2026-07-05T08:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"QDA35CBL","created_at":"2026-07-05T08:01:39Z"}],"graph_snapshots":[{"event_id":"sha256:86b497592c295e2d940597bba4c1bf4584a22301062af15f3697d597ee91a39e","target":"graph","created_at":"2026-07-05T08:01:39Z","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/2403.18361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from those seen during training. Our work introduces two key innovations to address this issue. Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration. Secondly, we introduce fuzzy positional encoding in the Vision Transformer to provide c","authors_text":"Hongxia Yang, Huaibo Huang, Qihang Fan, Quanzeng You, Ran He, Xiaotian Han, Yongfei Liu, Yunzhe Tao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T08:53:13Z","title":"ViTAR: Vision Transformer with Any Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18361","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":"sha256:09f47759583095316011db45510169fee583fa47239d713ce905e9f2f1dbe415","target":"record","created_at":"2026-07-05T08:01:39Z","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":"c23633c4bdce9845632498448eb56b4678c69ab902f0302ee1bd7159dbd3b461","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T08:53:13Z","title_canon_sha256":"d7a37d041710c66e387d16eea886195e78de5b41d2c5b1352c9c13645ee1fa98"},"schema_version":"1.0","source":{"id":"2403.18361","kind":"arxiv","version":2}},"canonical_sha256":"80c1be882b9f8a55d7b220406843126366a5d689ab419433f82b073195df1952","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80c1be882b9f8a55d7b220406843126366a5d689ab419433f82b073195df1952","first_computed_at":"2026-07-05T08:01:39.781474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:39.781474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d1yepMPigaTg3BH7X5c0Kwmxao5e3mMZut197Hp7m+qk1uyYabPygCUOaS4OafAD5JSahSyvmNrb9GIdgFIdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:39.781970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f47759583095316011db45510169fee583fa47239d713ce905e9f2f1dbe415","sha256:86b497592c295e2d940597bba4c1bf4584a22301062af15f3697d597ee91a39e"],"state_sha256":"48402293c1b303d23f11b0f024b4b1b60cd9ba1aeb8bd03e202679afad772946"}