{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:457664L75GLXTZE62WLWAW7P63","short_pith_number":"pith:457664L7","schema_version":"1.0","canonical_sha256":"e77fef717fe99779e49ed597605beff6c75a41f769e9013972fc0e63de44eb5e","source":{"kind":"arxiv","id":"2202.07630","version":2},"attestation_state":"computed","paper":{"title":"Delving Deeper into Cross-lingual Visual Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Chen Liu, Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2022-02-15T18:22:18Z","abstract_excerpt":"Visual question answering (VQA) is one of the crucial vision-and-language tasks. Yet, existing VQA research has mostly focused on the English language, due to a lack of suitable evaluation resources. Previous work on cross-lingual VQA has reported poor zero-shot transfer performance of current multilingual multimodal Transformers with large gaps to monolingual performance, without any deeper analysis. In this work, we delve deeper into the different aspects of cross-lingual VQA, aiming to understand the impact of 1) modeling methods and choices, including architecture, inductive bias, fine-tun"},"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":"2202.07630","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-15T18:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"547bfff0b11816bbab0a47df3cbd307523ae764f04a88f55294610ac55955dde","abstract_canon_sha256":"131c189338d3ff5b3ac881780c1befa081c015845a5289059360a4fd414f65cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:58.645652Z","signature_b64":"IhhNclg0rqGYRqi7ApxdrBr1bBM3udtW0YOspoYBbG1aoQUygNsle0gb4UQ6ix7V4Y+vKniTViDKX5gOBETJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e77fef717fe99779e49ed597605beff6c75a41f769e9013972fc0e63de44eb5e","last_reissued_at":"2026-07-05T06:18:58.645239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:58.645239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving Deeper into Cross-lingual Visual Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Chen Liu, Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2022-02-15T18:22:18Z","abstract_excerpt":"Visual question answering (VQA) is one of the crucial vision-and-language tasks. Yet, existing VQA research has mostly focused on the English language, due to a lack of suitable evaluation resources. Previous work on cross-lingual VQA has reported poor zero-shot transfer performance of current multilingual multimodal Transformers with large gaps to monolingual performance, without any deeper analysis. In this work, we delve deeper into the different aspects of cross-lingual VQA, aiming to understand the impact of 1) modeling methods and choices, including architecture, inductive bias, fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07630","kind":"arxiv","version":2},"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/2202.07630/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":"2202.07630","created_at":"2026-07-05T06:18:58.645293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07630v2","created_at":"2026-07-05T06:18:58.645293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07630","created_at":"2026-07-05T06:18:58.645293+00:00"},{"alias_kind":"pith_short_12","alias_value":"457664L75GLX","created_at":"2026-07-05T06:18:58.645293+00:00"},{"alias_kind":"pith_short_16","alias_value":"457664L75GLXTZE6","created_at":"2026-07-05T06:18:58.645293+00:00"},{"alias_kind":"pith_short_8","alias_value":"457664L7","created_at":"2026-07-05T06:18:58.645293+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/457664L75GLXTZE62WLWAW7P63","json":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63.json","graph_json":"https://pith.science/api/pith-number/457664L75GLXTZE62WLWAW7P63/graph.json","events_json":"https://pith.science/api/pith-number/457664L75GLXTZE62WLWAW7P63/events.json","paper":"https://pith.science/paper/457664L7"},"agent_actions":{"view_html":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63","download_json":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63.json","view_paper":"https://pith.science/paper/457664L7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07630&json=true","fetch_graph":"https://pith.science/api/pith-number/457664L75GLXTZE62WLWAW7P63/graph.json","fetch_events":"https://pith.science/api/pith-number/457664L75GLXTZE62WLWAW7P63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63/action/storage_attestation","attest_author":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63/action/author_attestation","sign_citation":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63/action/citation_signature","submit_replication":"https://pith.science/pith/457664L75GLXTZE62WLWAW7P63/action/replication_record"}},"created_at":"2026-07-05T06:18:58.645293+00:00","updated_at":"2026-07-05T06:18:58.645293+00:00"}