{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TIS47PEIHXOHWLP4RHXASABYI2","short_pith_number":"pith:TIS47PEI","schema_version":"1.0","canonical_sha256":"9a25cfbc883ddc7b2dfc89ee09003846a30ce38f27c9e3cfde9038af30bf9fb7","source":{"kind":"arxiv","id":"2605.24675","version":1},"attestation_state":"computed","paper":{"title":"VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Huacan Wang, Lijie Wen, Ningyuan Deng, Ronghao Chen, Shaolin Zhu","submitted_at":"2026-05-23T17:25:45Z","abstract_excerpt":"Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within social media and e-commerce domains. Although Large Vision-Language Models (LVLMs) have advanced multimodal understanding, applying them to Web image translation remains challenging due to the visual representation gap: standard encoders often prioritize high-level semantics over the fine-grained visual details required for recognizing diverse character morphologies. To address this challenge, we propose VaaWIT, an end-to-end framework that adapts "},"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":"2605.24675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T17:25:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6aa3ad4e7590661e400a2504cec25457c55ccebd81628f9349bb4bba4e16e36e","abstract_canon_sha256":"fd4a759e9fe71d415cd14e8ea2880fa39cd1d1635c91c3391672da0dc3b7f1cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:52.654810Z","signature_b64":"Q2dRbHnbFDvOjl6vsC48BTYt6U3rZHyeGZJUJxl2M+8bm6czVcldE+AOoWVjZl2YX7qrucUC3HOkN4TKM4VxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a25cfbc883ddc7b2dfc89ee09003846a30ce38f27c9e3cfde9038af30bf9fb7","last_reissued_at":"2026-05-26T01:03:52.653973Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:52.653973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Huacan Wang, Lijie Wen, Ningyuan Deng, Ronghao Chen, Shaolin Zhu","submitted_at":"2026-05-23T17:25:45Z","abstract_excerpt":"Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within social media and e-commerce domains. Although Large Vision-Language Models (LVLMs) have advanced multimodal understanding, applying them to Web image translation remains challenging due to the visual representation gap: standard encoders often prioritize high-level semantics over the fine-grained visual details required for recognizing diverse character morphologies. To address this challenge, we propose VaaWIT, an end-to-end framework that adapts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24675","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/2605.24675/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":"2605.24675","created_at":"2026-05-26T01:03:52.654115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24675v1","created_at":"2026-05-26T01:03:52.654115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24675","created_at":"2026-05-26T01:03:52.654115+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIS47PEIHXOH","created_at":"2026-05-26T01:03:52.654115+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIS47PEIHXOHWLP4","created_at":"2026-05-26T01:03:52.654115+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIS47PEI","created_at":"2026-05-26T01:03:52.654115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2","json":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2.json","graph_json":"https://pith.science/api/pith-number/TIS47PEIHXOHWLP4RHXASABYI2/graph.json","events_json":"https://pith.science/api/pith-number/TIS47PEIHXOHWLP4RHXASABYI2/events.json","paper":"https://pith.science/paper/TIS47PEI"},"agent_actions":{"view_html":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2","download_json":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2.json","view_paper":"https://pith.science/paper/TIS47PEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24675&json=true","fetch_graph":"https://pith.science/api/pith-number/TIS47PEIHXOHWLP4RHXASABYI2/graph.json","fetch_events":"https://pith.science/api/pith-number/TIS47PEIHXOHWLP4RHXASABYI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2/action/storage_attestation","attest_author":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2/action/author_attestation","sign_citation":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2/action/citation_signature","submit_replication":"https://pith.science/pith/TIS47PEIHXOHWLP4RHXASABYI2/action/replication_record"}},"created_at":"2026-05-26T01:03:52.654115+00:00","updated_at":"2026-05-26T01:03:52.654115+00:00"}