{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ECQNKNX7KGDBIVSKR6CCL35NI2","short_pith_number":"pith:ECQNKNX7","schema_version":"1.0","canonical_sha256":"20a0d536ff518614564a8f8425efad46b51015c27817b0bda147e83cf5c62050","source":{"kind":"arxiv","id":"2209.05401","version":3},"attestation_state":"computed","paper":{"title":"MaXM: Towards Multilingual Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ashish V. Thapliyal, Idan Szpektor, Julien Amelot, Linting Xue, Michal Yarom, Radu Soricut, Soravit Changpinyo, Xi Chen","submitted_at":"2022-09-12T16:53:37Z","abstract_excerpt":"Visual Question Answering (VQA) has been primarily studied through the lens of the English language. Yet, tackling VQA in other languages in the same manner would require a considerable amount of resources. In this paper, we propose scalable solutions to multilingual visual question answering (mVQA), on both data and modeling fronts. We first propose a translation-based framework to mVQA data generation that requires much less human annotation efforts than the conventional approach of directly collection questions and answers. Then, we apply our framework to the multilingual captions in the Cr"},"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":"2209.05401","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-12T16:53:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e0dcd05ebf520af8b666f6d28ddf47ce3b6e8f3d8442c1050c6b51d508b65399","abstract_canon_sha256":"18f96b6332e055bc8e95a41b223eab1cc01bd22fe01bee035c1d1cca5b7013cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:11.120701Z","signature_b64":"SfKSrIBZU68wZdISaEMrgTDa5F1uIgj8sYicLeOYggEsYHs+Rn/0P09oxSFFZ22RymkOQOeaZ3ebJgWspQHkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20a0d536ff518614564a8f8425efad46b51015c27817b0bda147e83cf5c62050","last_reissued_at":"2026-07-05T07:04:11.120190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:11.120190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaXM: Towards Multilingual Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ashish V. Thapliyal, Idan Szpektor, Julien Amelot, Linting Xue, Michal Yarom, Radu Soricut, Soravit Changpinyo, Xi Chen","submitted_at":"2022-09-12T16:53:37Z","abstract_excerpt":"Visual Question Answering (VQA) has been primarily studied through the lens of the English language. Yet, tackling VQA in other languages in the same manner would require a considerable amount of resources. In this paper, we propose scalable solutions to multilingual visual question answering (mVQA), on both data and modeling fronts. We first propose a translation-based framework to mVQA data generation that requires much less human annotation efforts than the conventional approach of directly collection questions and answers. Then, we apply our framework to the multilingual captions in the Cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05401","kind":"arxiv","version":3},"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/2209.05401/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":"2209.05401","created_at":"2026-07-05T07:04:11.120249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05401v3","created_at":"2026-07-05T07:04:11.120249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05401","created_at":"2026-07-05T07:04:11.120249+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECQNKNX7KGDB","created_at":"2026-07-05T07:04:11.120249+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECQNKNX7KGDBIVSK","created_at":"2026-07-05T07:04:11.120249+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECQNKNX7","created_at":"2026-07-05T07:04:11.120249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2209.06794","citing_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2","json":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2.json","graph_json":"https://pith.science/api/pith-number/ECQNKNX7KGDBIVSKR6CCL35NI2/graph.json","events_json":"https://pith.science/api/pith-number/ECQNKNX7KGDBIVSKR6CCL35NI2/events.json","paper":"https://pith.science/paper/ECQNKNX7"},"agent_actions":{"view_html":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2","download_json":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2.json","view_paper":"https://pith.science/paper/ECQNKNX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05401&json=true","fetch_graph":"https://pith.science/api/pith-number/ECQNKNX7KGDBIVSKR6CCL35NI2/graph.json","fetch_events":"https://pith.science/api/pith-number/ECQNKNX7KGDBIVSKR6CCL35NI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2/action/storage_attestation","attest_author":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2/action/author_attestation","sign_citation":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2/action/citation_signature","submit_replication":"https://pith.science/pith/ECQNKNX7KGDBIVSKR6CCL35NI2/action/replication_record"}},"created_at":"2026-07-05T07:04:11.120249+00:00","updated_at":"2026-07-05T07:04:11.120249+00:00"}