{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SE6IDNWP4ULJ2CKDGIEPR4JJGO","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":"1917e34a031ab8dd10ccc5876d90d963de8349f3f284938c01d74f80f136f695","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-09T02:52:47Z","title_canon_sha256":"992b76cffb88f632f1f91a18618b087c4d62b296cf37e53f54d28bf99443f5f9"},"schema_version":"1.0","source":{"id":"2305.05140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05140","created_at":"2026-07-05T06:08:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05140v2","created_at":"2026-07-05T06:08:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05140","created_at":"2026-07-05T06:08:55Z"},{"alias_kind":"pith_short_12","alias_value":"SE6IDNWP4ULJ","created_at":"2026-07-05T06:08:55Z"},{"alias_kind":"pith_short_16","alias_value":"SE6IDNWP4ULJ2CKD","created_at":"2026-07-05T06:08:55Z"},{"alias_kind":"pith_short_8","alias_value":"SE6IDNWP","created_at":"2026-07-05T06:08:55Z"}],"graph_snapshots":[{"event_id":"sha256:0ae85bd67d5ebd2f52ef30c1ead779faa7a09c19d7c04508636c12a0bde22d17","target":"graph","created_at":"2026-07-05T06:08:55Z","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/2305.05140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two problems: (1) the pure vision-based query results in attention drift, which usually causes poor recognition and is summarized as linguistic insensitive drift (LID) problem in this paper. (2) the visual feature is suboptimal for the recognition in some vision-missing cases (e.g. occlusion, etc.). To address these issues, we propose a $\\textbf{L}$inguistic $\\t","authors_text":"Boqiang Zhang, Hongtao Xie, Jianjun Xu, Yongdong Zhang, Yuxin Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-09T02:52:47Z","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05140","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:b0f4018c59bc68c703e294685f40eadeb912dc6624ae4194f9a7a4bf18516018","target":"record","created_at":"2026-07-05T06:08:55Z","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":"1917e34a031ab8dd10ccc5876d90d963de8349f3f284938c01d74f80f136f695","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-09T02:52:47Z","title_canon_sha256":"992b76cffb88f632f1f91a18618b087c4d62b296cf37e53f54d28bf99443f5f9"},"schema_version":"1.0","source":{"id":"2305.05140","kind":"arxiv","version":2}},"canonical_sha256":"913c81b6cfe5169d09433208f8f12933a5ba73f0ead120de0182a7d2faaf6da7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"913c81b6cfe5169d09433208f8f12933a5ba73f0ead120de0182a7d2faaf6da7","first_computed_at":"2026-07-05T06:08:55.959161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:55.959161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a6pYHnF6nUBmtuPn+OVkD3aCZ7hgr/AcywuvgMrLN1Y2ues7Pll5pOajLOOllhgzhYd3m//1gWxZPKxDxj2ABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:55.959607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0f4018c59bc68c703e294685f40eadeb912dc6624ae4194f9a7a4bf18516018","sha256:0ae85bd67d5ebd2f52ef30c1ead779faa7a09c19d7c04508636c12a0bde22d17"],"state_sha256":"0592396d9632d6e58d151092d05accfcb3dcf051abf7d278e99fb631f3cf3c9b"}