{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MISURGFLYJYJ3RLTKPX3CB6YX5","short_pith_number":"pith:MISURGFL","schema_version":"1.0","canonical_sha256":"62254898abc2709dc57353efb107d8bf6aa418be9cef8bfec5998a7c3fcef6df","source":{"kind":"arxiv","id":"2412.14596","version":1},"attestation_state":"computed","paper":{"title":"LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gengluo Li, Huawen Shen, Jinwen Zhong, Yu Zhou","submitted_at":"2024-12-19T07:31:40Z","abstract_excerpt":"Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually English). Due to the extremely unbalanced quantity and quality of pre-training corpora between English and other languages, few works can extend to non-English scenarios. In this paper, we conduct systematic experiments to show that vision and layout modality hold invariance among images with different languages. If decoupling language bias from document images"},"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":"2412.14596","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T07:31:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"241aa6119ae758055c5c80eac1b239284629c76ef824dc265465ea89740bfc9f","abstract_canon_sha256":"aa524465117c3f05bd3a27278c9b5230a4e4d46a8ef6bdbc3f1f53fcc6085abd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:49.972861Z","signature_b64":"VufgpZshCaKAYESB3Mg0if1vlqErsXEYHggE4+LjBdOljuKsWnh9Y3RgfamHC8Y/W5Xgiz+XzeIm2xTdO8baDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62254898abc2709dc57353efb107d8bf6aa418be9cef8bfec5998a7c3fcef6df","last_reissued_at":"2026-07-05T09:51:49.972370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:49.972370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gengluo Li, Huawen Shen, Jinwen Zhong, Yu Zhou","submitted_at":"2024-12-19T07:31:40Z","abstract_excerpt":"Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually English). Due to the extremely unbalanced quantity and quality of pre-training corpora between English and other languages, few works can extend to non-English scenarios. In this paper, we conduct systematic experiments to show that vision and layout modality hold invariance among images with different languages. If decoupling language bias from document images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14596","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/2412.14596/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":"2412.14596","created_at":"2026-07-05T09:51:49.972433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14596v1","created_at":"2026-07-05T09:51:49.972433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14596","created_at":"2026-07-05T09:51:49.972433+00:00"},{"alias_kind":"pith_short_12","alias_value":"MISURGFLYJYJ","created_at":"2026-07-05T09:51:49.972433+00:00"},{"alias_kind":"pith_short_16","alias_value":"MISURGFLYJYJ3RLT","created_at":"2026-07-05T09:51:49.972433+00:00"},{"alias_kind":"pith_short_8","alias_value":"MISURGFL","created_at":"2026-07-05T09:51:49.972433+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/MISURGFLYJYJ3RLTKPX3CB6YX5","json":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5.json","graph_json":"https://pith.science/api/pith-number/MISURGFLYJYJ3RLTKPX3CB6YX5/graph.json","events_json":"https://pith.science/api/pith-number/MISURGFLYJYJ3RLTKPX3CB6YX5/events.json","paper":"https://pith.science/paper/MISURGFL"},"agent_actions":{"view_html":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5","download_json":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5.json","view_paper":"https://pith.science/paper/MISURGFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14596&json=true","fetch_graph":"https://pith.science/api/pith-number/MISURGFLYJYJ3RLTKPX3CB6YX5/graph.json","fetch_events":"https://pith.science/api/pith-number/MISURGFLYJYJ3RLTKPX3CB6YX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5/action/storage_attestation","attest_author":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5/action/author_attestation","sign_citation":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5/action/citation_signature","submit_replication":"https://pith.science/pith/MISURGFLYJYJ3RLTKPX3CB6YX5/action/replication_record"}},"created_at":"2026-07-05T09:51:49.972433+00:00","updated_at":"2026-07-05T09:51:49.972433+00:00"}