{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YGC7BLHEADWF4MD34AL7PI5UJ3","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":"cde41d664379c5d112c722097f96f1abb3a0b1e77d17e4386cc914d184dfa151","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T15:58:21Z","title_canon_sha256":"a96299ed8e8df0fda011f764b2b0675d29e490121f14585129422720aa016c2c"},"schema_version":"1.0","source":{"id":"2109.06082","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06082","created_at":"2026-07-05T04:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06082v2","created_at":"2026-07-05T04:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06082","created_at":"2026-07-05T04:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"YGC7BLHEADWF","created_at":"2026-07-05T04:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"YGC7BLHEADWF4MD3","created_at":"2026-07-05T04:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"YGC7BLHE","created_at":"2026-07-05T04:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:47d87d8ea3070624761227c6a9899cf10d0ffbe3d0c28e1182a8930538e2f713","target":"graph","created_at":"2026-07-05T04:05:59Z","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/2109.06082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal vision and language modeling have predominantly focused on the English language, mostly due to the lack of multilingual multimodal datasets to steer modeling efforts. In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task. We extend the established English GQA dataset to 7 typologically diverse languages, enabling us to detect and explore crucial challenges in cross-lingual visual question answering. We further propose new adapter-based approaches to adapt multimodal transformer-based mode","authors_text":"Aishwarya Kamath, Gregor Geigle, Iryna Gurevych, Ivan Vuli\\'c, Jan-Martin O. Steitz, Jonas Pfeiffer, Stefan Roth","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T15:58:21Z","title":"xGQA: Cross-Lingual Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06082","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":"sha256:7b0186b0304802ae8df869fc99deb8ba199343523916142bc8035160736d4f0f","target":"record","created_at":"2026-07-05T04:05:59Z","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":"cde41d664379c5d112c722097f96f1abb3a0b1e77d17e4386cc914d184dfa151","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T15:58:21Z","title_canon_sha256":"a96299ed8e8df0fda011f764b2b0675d29e490121f14585129422720aa016c2c"},"schema_version":"1.0","source":{"id":"2109.06082","kind":"arxiv","version":2}},"canonical_sha256":"c185f0ace400ec5e307be017f7a3b44ec1659654556f25556544263fda79e676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c185f0ace400ec5e307be017f7a3b44ec1659654556f25556544263fda79e676","first_computed_at":"2026-07-05T04:05:59.671200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:59.671200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0RxHu+Ueiev+W5VGDUxaWldoYfYfCBfKQpWQjIyl07+Tju6N6LQmSXO2jjH4xY7GOVOwBG0W8EQ37DjmIVa5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:59.671631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06082","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b0186b0304802ae8df869fc99deb8ba199343523916142bc8035160736d4f0f","sha256:47d87d8ea3070624761227c6a9899cf10d0ffbe3d0c28e1182a8930538e2f713"],"state_sha256":"5e6b894bb9ad12391039505386c5ac3b22d83f88703a69cc7231c49e498fc9af"}