{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ACZUUHXXMZ3SS4DJVWRSZORODQ","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":"f72c27c0528771a6d26dd288717aa15659df79bc804ae5feb3eff227d5969013","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T10:39:46Z","title_canon_sha256":"6bfaf8d13740cc0c56215b3cb43f902d7d7b366419e8a192415271638acdba17"},"schema_version":"1.0","source":{"id":"2304.00287","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00287","created_at":"2026-07-05T06:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00287v2","created_at":"2026-07-05T06:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00287","created_at":"2026-07-05T06:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"ACZUUHXXMZ3S","created_at":"2026-07-05T06:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"ACZUUHXXMZ3SS4DJ","created_at":"2026-07-05T06:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"ACZUUHXX","created_at":"2026-07-05T06:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:0e130fb6316925cd39741561247e742c18c13a6565110cb699e3b020038bf954","target":"graph","created_at":"2026-07-05T06:04:55Z","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/2304.00287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword - a chunk of raw data of arbitrary size. In this work, we apply this approach to Vision Transformers by introducing a novel image tokenization scheme, replacing the standard uniform grid with a mixed-resolution sequence of tokens, where each token represents a patch of arbitrary size. Using the Quadtree algorithm and a novel saliency scorer, we construct a p","authors_text":"Avram Golbert, Omer Levy, Tomer Ronen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T10:39:46Z","title":"Vision Transformers with Mixed-Resolution Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00287","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":"sha256:0245ca80e9c61f9266d8e37c8cc12feeb452028a47abeef545474dd7b51c1251","target":"record","created_at":"2026-07-05T06:04:55Z","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":"f72c27c0528771a6d26dd288717aa15659df79bc804ae5feb3eff227d5969013","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T10:39:46Z","title_canon_sha256":"6bfaf8d13740cc0c56215b3cb43f902d7d7b366419e8a192415271638acdba17"},"schema_version":"1.0","source":{"id":"2304.00287","kind":"arxiv","version":2}},"canonical_sha256":"00b34a1ef76677297069ada32cba2e1c284c22103505cdc3e4d5134b58890941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00b34a1ef76677297069ada32cba2e1c284c22103505cdc3e4d5134b58890941","first_computed_at":"2026-07-05T06:04:55.230369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:55.230369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pLlTIXfNktrwEPKLafYdg+yyeDjOevMJn8dsVmOYerjC4U6JBnT7Cqjb0/UDZNXF62Qy19qzY+uPrsOVN02nBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:55.230756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00287","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0245ca80e9c61f9266d8e37c8cc12feeb452028a47abeef545474dd7b51c1251","sha256:0e130fb6316925cd39741561247e742c18c13a6565110cb699e3b020038bf954"],"state_sha256":"efb688f1967bf6c0e6959ab28699662ac1015ab04a4264e218a0a9ba317bbf4c"}