{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6VU4MKF6AE53LCXCH2BZLHEEMC","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":"515327e03b13e125f96aa588a60d6b44c329bb096c78bed145648fb54032a932","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-25T14:38:47Z","title_canon_sha256":"597fbd7f5168dc94630331a13004ad29592e142ccc3d5ef3a4cc884b2a518164"},"schema_version":"1.0","source":{"id":"2602.21956","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.21956","created_at":"2026-08-17T01:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2602.21956v2","created_at":"2026-08-17T01:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21956","created_at":"2026-08-17T01:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"6VU4MKF6AE53","created_at":"2026-08-17T01:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"6VU4MKF6AE53LCXC","created_at":"2026-08-17T01:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"6VU4MKF6","created_at":"2026-08-17T01:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:60fdc96738e226005b19d91a8e61aadec8f5087a79965354912b00a0a91e9509","target":"graph","created_at":"2026-08-17T01:09:48Z","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/2602.21956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text Image Machine Translation (TIMT) aims to translate text embedded in images in the source-language into target-language, requiring synergistic integration of visual perception and linguistic understanding. Existing TIMT methods, whether cascaded pipelines or end-to-end multimodal large language models (MLLMs),struggle with high-resolution text-rich images due to cluttered layouts, diverse fonts, and non-textual distractions, resulting in text omission, semantic drift, and contextual inconsistency. To address these challenges, we propose GLoTran, a global-local dual visual perception framew","authors_text":"Daimeng Wei, Hui Yang, Jing Zhao, Junxin Lu, Kun Chen, Ning Xie, Pengfei Li, Shiliang Sun, Tengfei Song, Xiaowei Liang, Yunfei Lu, Zhanglin Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-25T14:38:47Z","title":"Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21956","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":"sha256:726930b552534fc1ea57cc631e93ffcb848c00d8e5514e07d920c0076e2fc5a7","target":"record","created_at":"2026-08-17T01:09:48Z","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":"515327e03b13e125f96aa588a60d6b44c329bb096c78bed145648fb54032a932","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-25T14:38:47Z","title_canon_sha256":"597fbd7f5168dc94630331a13004ad29592e142ccc3d5ef3a4cc884b2a518164"},"schema_version":"1.0","source":{"id":"2602.21956","kind":"arxiv","version":2}},"canonical_sha256":"f569c628be013bb58ae23e83959c8460a0af19edc67cfc5f8636c1dcd6ca74f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f569c628be013bb58ae23e83959c8460a0af19edc67cfc5f8636c1dcd6ca74f1","first_computed_at":"2026-08-17T01:09:48.758617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-17T01:09:48.758617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CREcVIl/Z2mty7eZ0dQTSZKFeRU2orJiNgpshVZFTqL5bVQm06xKgweMWmh+N9rtKkyHGlvYWkNJaaW5LUuLCw==","signature_status":"signed_v1","signed_at":"2026-08-17T01:09:48.761271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.21956","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:726930b552534fc1ea57cc631e93ffcb848c00d8e5514e07d920c0076e2fc5a7","sha256:60fdc96738e226005b19d91a8e61aadec8f5087a79965354912b00a0a91e9509"],"state_sha256":"116eb690328a9fb166fb8b60b740897df30f462150b8a4c48890f52f782af991"}