{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BGCJSIF4JMU2Z655AXNVVPBIEI","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":"fc9f6b8af345c4f9ca5f69a6165176f66bfbc21df77bb71f18163352cb527b41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T04:26:17Z","title_canon_sha256":"9d117eada7210740cec4ae288ad3250362c0afa07500a88cc761a4149734d3a0"},"schema_version":"1.0","source":{"id":"2312.06109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06109","created_at":"2026-07-05T07:22:38Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06109v1","created_at":"2026-07-05T07:22:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06109","created_at":"2026-07-05T07:22:38Z"},{"alias_kind":"pith_short_12","alias_value":"BGCJSIF4JMU2","created_at":"2026-07-05T07:22:38Z"},{"alias_kind":"pith_short_16","alias_value":"BGCJSIF4JMU2Z655","created_at":"2026-07-05T07:22:38Z"},{"alias_kind":"pith_short_8","alias_value":"BGCJSIF4","created_at":"2026-07-05T07:22:38Z"}],"graph_snapshots":[{"event_id":"sha256:140fd6cec2eefaf3d2d7c4de55611722928854f830b5fc346eb03e0a5e22dc36","target":"graph","created_at":"2026-07-05T07:22:38Z","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/2312.06109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern Large Vision-Language Models (LVLMs) enjoy the same vision vocabulary -- CLIP, which can cover most common vision tasks. However, for some special vision task that needs dense and fine-grained vision perception, e.g., document-level OCR or chart understanding, especially in non-English scenarios, the CLIP-style vocabulary may encounter low efficiency in tokenizing the vision knowledge and even suffer out-of-vocabulary problem. Accordingly, we propose Vary, an efficient and effective method to scale up the vision vocabulary of LVLMs. The procedures of Vary are naturally divided into two ","authors_text":"Chunrui Han, Haoran Wei, Jianjian Sun, Jinrong Yang, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T04:26:17Z","title":"Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06109","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:a28e5455bcc4b89a6b707699d0f44bd3ce1d1b3e653991d7b4d2105085f8f771","target":"record","created_at":"2026-07-05T07:22:38Z","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":"fc9f6b8af345c4f9ca5f69a6165176f66bfbc21df77bb71f18163352cb527b41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T04:26:17Z","title_canon_sha256":"9d117eada7210740cec4ae288ad3250362c0afa07500a88cc761a4149734d3a0"},"schema_version":"1.0","source":{"id":"2312.06109","kind":"arxiv","version":1}},"canonical_sha256":"09849920bc4b29acfbbd05db5abc2822219e4a69f066e8b710fb58783447cd81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09849920bc4b29acfbbd05db5abc2822219e4a69f066e8b710fb58783447cd81","first_computed_at":"2026-07-05T07:22:38.777714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:38.777714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8daiGQjlqjs4fkiy8QQ22DuE5ABEVMq5vNSgzL1izL9IdUIsEHKOPf304f/30ua7nmglwD3u7NqAanl8Wta9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:38.778209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a28e5455bcc4b89a6b707699d0f44bd3ce1d1b3e653991d7b4d2105085f8f771","sha256:140fd6cec2eefaf3d2d7c4de55611722928854f830b5fc346eb03e0a5e22dc36"],"state_sha256":"b3afb6e8c2c8f1781c36f36a5612789d51d60ff0620a08b470ad1797de5b1bd2"}