{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SEEM3JB5T7FPUG6RT2BF22XKES","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":"8472f52d543151bea5d51145b7ab5e82c83765d23cea37074140cb721b097d55","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T11:37:48Z","title_canon_sha256":"61c4462802f511e637d0b3a367fd4122637bf2ad8b558f0923377a0af6abfc7c"},"schema_version":"1.0","source":{"id":"2406.11432","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11432","created_at":"2026-07-05T08:32:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11432v1","created_at":"2026-07-05T08:32:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11432","created_at":"2026-07-05T08:32:53Z"},{"alias_kind":"pith_short_12","alias_value":"SEEM3JB5T7FP","created_at":"2026-07-05T08:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SEEM3JB5T7FPUG6R","created_at":"2026-07-05T08:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SEEM3JB5","created_at":"2026-07-05T08:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:06259385f93c79d2ecaa80b95900d51203fdde6b617d0ea894dd0fa73a52c45e","target":"graph","created_at":"2026-07-05T08:32:53Z","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/2406.11432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces AnyTrans, an all-encompassing framework for the task-Translate AnyText in the Image (TATI), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, the advanced inpainting and editing abilities of diffu","authors_text":"Baosong Yang, Derek F. Wong, Kai Fan, Pei Zhang, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma, Zhipeng Qian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T11:37:48Z","title":"AnyTrans: Translate AnyText in the Image with Large Scale Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11432","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:ff063803b040a4a657b4df123cd3346496c3f63a6a54c40bc776b9ed6e491958","target":"record","created_at":"2026-07-05T08:32:53Z","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":"8472f52d543151bea5d51145b7ab5e82c83765d23cea37074140cb721b097d55","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T11:37:48Z","title_canon_sha256":"61c4462802f511e637d0b3a367fd4122637bf2ad8b558f0923377a0af6abfc7c"},"schema_version":"1.0","source":{"id":"2406.11432","kind":"arxiv","version":1}},"canonical_sha256":"9108cda43d9fcafa1bd19e825d6aea24b76042bbdbf0e0575ac5d1a783f036c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9108cda43d9fcafa1bd19e825d6aea24b76042bbdbf0e0575ac5d1a783f036c1","first_computed_at":"2026-07-05T08:32:53.252537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:53.252537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6wO1PaVdU3GrNQRHjaY/eBK+MKJ3YhTvLE3bKCa7IOIxr414jtJc5OXGWdMp1/p43puNrkTXhzXjFILBXyT2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:53.253008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11432","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff063803b040a4a657b4df123cd3346496c3f63a6a54c40bc776b9ed6e491958","sha256:06259385f93c79d2ecaa80b95900d51203fdde6b617d0ea894dd0fa73a52c45e"],"state_sha256":"cbae3e32fd0e681f69dab1d5403135152ed6e331a7f0cd4d83175a58f5155f01"}