{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SEEM3JB5T7FPUG6RT2BF22XKES","short_pith_number":"pith:SEEM3JB5","schema_version":"1.0","canonical_sha256":"9108cda43d9fcafa1bd19e825d6aea24b76042bbdbf0e0575ac5d1a783f036c1","source":{"kind":"arxiv","id":"2406.11432","version":1},"attestation_state":"computed","paper":{"title":"AnyTrans: Translate AnyText in the Image with Large Scale Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baosong Yang, Derek F. Wong, Kai Fan, Pei Zhang, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma, Zhipeng Qian","submitted_at":"2024-06-17T11:37:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.11432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T11:37:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61c4462802f511e637d0b3a367fd4122637bf2ad8b558f0923377a0af6abfc7c","abstract_canon_sha256":"8472f52d543151bea5d51145b7ab5e82c83765d23cea37074140cb721b097d55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:53.253008Z","signature_b64":"6wO1PaVdU3GrNQRHjaY/eBK+MKJ3YhTvLE3bKCa7IOIxr414jtJc5OXGWdMp1/p43puNrkTXhzXjFILBXyT2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9108cda43d9fcafa1bd19e825d6aea24b76042bbdbf0e0575ac5d1a783f036c1","last_reissued_at":"2026-07-05T08:32:53.252537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:53.252537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnyTrans: Translate AnyText in the Image with Large Scale Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baosong Yang, Derek F. Wong, Kai Fan, Pei Zhang, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma, Zhipeng Qian","submitted_at":"2024-06-17T11:37:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11432","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.11432/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.11432","created_at":"2026-07-05T08:32:53.252596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11432v1","created_at":"2026-07-05T08:32:53.252596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11432","created_at":"2026-07-05T08:32:53.252596+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEEM3JB5T7FP","created_at":"2026-07-05T08:32:53.252596+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEEM3JB5T7FPUG6R","created_at":"2026-07-05T08:32:53.252596+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEEM3JB5","created_at":"2026-07-05T08:32:53.252596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07572","citing_title":"Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES","json":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES.json","graph_json":"https://pith.science/api/pith-number/SEEM3JB5T7FPUG6RT2BF22XKES/graph.json","events_json":"https://pith.science/api/pith-number/SEEM3JB5T7FPUG6RT2BF22XKES/events.json","paper":"https://pith.science/paper/SEEM3JB5"},"agent_actions":{"view_html":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES","download_json":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES.json","view_paper":"https://pith.science/paper/SEEM3JB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11432&json=true","fetch_graph":"https://pith.science/api/pith-number/SEEM3JB5T7FPUG6RT2BF22XKES/graph.json","fetch_events":"https://pith.science/api/pith-number/SEEM3JB5T7FPUG6RT2BF22XKES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES/action/storage_attestation","attest_author":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES/action/author_attestation","sign_citation":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES/action/citation_signature","submit_replication":"https://pith.science/pith/SEEM3JB5T7FPUG6RT2BF22XKES/action/replication_record"}},"created_at":"2026-07-05T08:32:53.252596+00:00","updated_at":"2026-07-05T08:32:53.252596+00:00"}