{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:457664L75GLXTZE62WLWAW7P63","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":"131c189338d3ff5b3ac881780c1befa081c015845a5289059360a4fd414f65cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-15T18:22:18Z","title_canon_sha256":"547bfff0b11816bbab0a47df3cbd307523ae764f04a88f55294610ac55955dde"},"schema_version":"1.0","source":{"id":"2202.07630","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07630","created_at":"2026-07-05T06:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07630v2","created_at":"2026-07-05T06:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07630","created_at":"2026-07-05T06:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"457664L75GLX","created_at":"2026-07-05T06:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"457664L75GLXTZE6","created_at":"2026-07-05T06:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"457664L7","created_at":"2026-07-05T06:18:58Z"}],"graph_snapshots":[{"event_id":"sha256:9874253c1af826e37f5b5ab64cc111ba9eeda04cec11b0876535d1d901b5a59b","target":"graph","created_at":"2026-07-05T06:18:58Z","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/2202.07630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anna Korhonen, Chen Liu, Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-15T18:22:18Z","title":"Delving Deeper into Cross-lingual Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07630","kind":"arxiv","version":2},"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:d24ce7771e283c5daf0f84fdc2e44bd8ab8127634b590d710b5ae75eb000e5b2","target":"record","created_at":"2026-07-05T06:18:58Z","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":"131c189338d3ff5b3ac881780c1befa081c015845a5289059360a4fd414f65cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-15T18:22:18Z","title_canon_sha256":"547bfff0b11816bbab0a47df3cbd307523ae764f04a88f55294610ac55955dde"},"schema_version":"1.0","source":{"id":"2202.07630","kind":"arxiv","version":2}},"canonical_sha256":"e77fef717fe99779e49ed597605beff6c75a41f769e9013972fc0e63de44eb5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e77fef717fe99779e49ed597605beff6c75a41f769e9013972fc0e63de44eb5e","first_computed_at":"2026-07-05T06:18:58.645239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:58.645239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IhhNclg0rqGYRqi7ApxdrBr1bBM3udtW0YOspoYBbG1aoQUygNsle0gb4UQ6ix7V4Y+vKniTViDKX5gOBETJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:58.645652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.07630","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d24ce7771e283c5daf0f84fdc2e44bd8ab8127634b590d710b5ae75eb000e5b2","sha256:9874253c1af826e37f5b5ab64cc111ba9eeda04cec11b0876535d1d901b5a59b"],"state_sha256":"9d92178a2fcf0dcff88a63224b30c22346b72377fbeff98caf099080baf9eadc"}