{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TLHUHC7TU447CWQTPCE4N6JPFS","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":"04c7be615e0c9469e996700d934c22503b31d007355150804ce6063dd7ef7ff3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T08:47:17Z","title_canon_sha256":"a52b27cb4301b78662422120214581d35b049755fef46d5582c374f99436c4d4"},"schema_version":"1.0","source":{"id":"2606.01911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01911","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01911v1","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01911","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"TLHUHC7TU447","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"TLHUHC7TU447CWQT","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"TLHUHC7T","created_at":"2026-06-02T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:5ce4e9c7aa9014c9479273f57f6e4094fb0da11f7fc3e5619867cff6814d5907","target":"graph","created_at":"2026-06-02T02:05:00Z","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/2606.01911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation ability, they still underperform on text rendering with blur strokes and disrupt letter shapes. In this work, we trace this limitation to the visual tokenizer, which struggles to reconstruct fine-grained detail. Improving the tokenizer is straightforward but expensive, as it necessitates retraining both the tokenizer and the AR model. Can we improve text rendering performance of AR models without retraining the existing to","authors_text":"Dongxing Mao, Jiahao Tang, Jingru Tan, Jinpeng Wang, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Min Li, Zhengyuan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T08:47:17Z","title":"Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01911","kind":"arxiv","version":1},"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:e5d9e45399304e5d5ef0801c80f6277290af8b55e48079dbdfa326de30ca4dd6","target":"record","created_at":"2026-06-02T02:05:00Z","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":"04c7be615e0c9469e996700d934c22503b31d007355150804ce6063dd7ef7ff3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T08:47:17Z","title_canon_sha256":"a52b27cb4301b78662422120214581d35b049755fef46d5582c374f99436c4d4"},"schema_version":"1.0","source":{"id":"2606.01911","kind":"arxiv","version":1}},"canonical_sha256":"9acf438bf3a739f15a137889c6f92f2cace9916c555c11e51cfa8233ec39d333","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9acf438bf3a739f15a137889c6f92f2cace9916c555c11e51cfa8233ec39d333","first_computed_at":"2026-06-02T02:05:00.227690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:00.227690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n6f7nAayvtomQow/DSSPRdjgvW/D8ijumnLz9vWgdt7Yc+jRBaUzqs0Ymj4fV7VmNzTBj4HvwWXb3RARc9vvBA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:00.228084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5d9e45399304e5d5ef0801c80f6277290af8b55e48079dbdfa326de30ca4dd6","sha256:5ce4e9c7aa9014c9479273f57f6e4094fb0da11f7fc3e5619867cff6814d5907"],"state_sha256":"762150269755316e8fd89d0d8b24c77d6e40ab16d52a1f1759923a1f2b3ae254"}