{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UOJKSSPHIHA5OCNCBQYZTN7MM5","short_pith_number":"pith:UOJKSSPH","canonical_record":{"source":{"id":"2405.11985","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T12:35:01Z","cross_cats_sorted":[],"title_canon_sha256":"777a20dbf4da8a4029a695ecff7601ceb5879082c8de6736d58ffdc42e02595d","abstract_canon_sha256":"24a3a16be9605a5c5e8ac0542e1b2eebf4b0ce7d2f4c46da3fe27b56c31c9806"},"schema_version":"1.0"},"canonical_sha256":"a392a949e741c1d709a20c3199b7ec676b46d955d8f0d5340083339625ae3c4c","source":{"kind":"arxiv","id":"2405.11985","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11985","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11985v5","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11985","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"UOJKSSPHIHA5","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"UOJKSSPHIHA5OCNC","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"UOJKSSPH","created_at":"2026-07-05T11:19:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UOJKSSPHIHA5OCNCBQYZTN7MM5","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11985","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T12:35:01Z","cross_cats_sorted":[],"title_canon_sha256":"777a20dbf4da8a4029a695ecff7601ceb5879082c8de6736d58ffdc42e02595d","abstract_canon_sha256":"24a3a16be9605a5c5e8ac0542e1b2eebf4b0ce7d2f4c46da3fe27b56c31c9806"},"schema_version":"1.0"},"canonical_sha256":"a392a949e741c1d709a20c3199b7ec676b46d955d8f0d5340083339625ae3c4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:19.429687Z","signature_b64":"ioo2DTmBoBAbOJfCpmvhtPJYDhBmdW3EhYFeDvht5FqxS/zNERHGo67PxP2MWqEY0lLBsH6agF0ZqQu6LwafAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a392a949e741c1d709a20c3199b7ec676b46d955d8f0d5340083339625ae3c4c","last_reissued_at":"2026-07-05T11:19:19.429171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:19.429171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11985","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wp/HpMohN06+kIo7ochLxI5QvMJvRowAfXsWu0bKhS+X+qnttSWD9XE2/1P4KR3GnERe1D8s+Gs3wix2EgOTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:45:53.577393Z"},"content_sha256":"bb0a161e3e2ba81803bbe203ba1f84c4120e3b1956b6eec849f3db2b6055bdab","schema_version":"1.0","event_id":"sha256:bb0a161e3e2ba81803bbe203ba1f84c4120e3b1956b6eec849f3db2b6055bdab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UOJKSSPHIHA5OCNCBQYZTN7MM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Huang, Chunhui Lin, Hao Feng, Hao Liu, Jinghui Lu, Jingqun Tang, Kuan Lu, Mohamad Fitri Faiz Bin Mahmood, Qi Liu, Shu Wei, Wanqing Li, Xiang Bai, Yangfan He, Yanjie Wang, YongJie Ye, Yuliang Liu, Zhen Zhao","submitted_at":"2024-05-20T12:35:01Z","abstract_excerpt":"Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding. Nonetheless, most existing TEC-VQA benchmarks have focused on high-resource languages like English and Chinese. Despite pioneering works to expand multilingual QA pairs in non-text-centric VQA datasets through translation engines, the translation-based protocol encounters a substantial \"visual-textual misalignment\" problem when app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11985","kind":"arxiv","version":5},"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/2405.11985/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ibnyaav663ouaGAnhfi475YCFpBlc6snkgu1z1T/8/HGdJ1N9xZe+bUQoaPsqJ11A1aIvIMDddA1VCruZlXHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:45:53.577884Z"},"content_sha256":"253ff71ef467510058a1d2f2ffe6050da3b0cebaeebaec7faf97a8651783bb10","schema_version":"1.0","event_id":"sha256:253ff71ef467510058a1d2f2ffe6050da3b0cebaeebaec7faf97a8651783bb10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5/bundle.json","state_url":"https://pith.science/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T07:45:53Z","links":{"resolver":"https://pith.science/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5","bundle":"https://pith.science/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5/bundle.json","state":"https://pith.science/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOJKSSPHIHA5OCNCBQYZTN7MM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UOJKSSPHIHA5OCNCBQYZTN7MM5","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":"24a3a16be9605a5c5e8ac0542e1b2eebf4b0ce7d2f4c46da3fe27b56c31c9806","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T12:35:01Z","title_canon_sha256":"777a20dbf4da8a4029a695ecff7601ceb5879082c8de6736d58ffdc42e02595d"},"schema_version":"1.0","source":{"id":"2405.11985","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11985","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11985v5","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11985","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"UOJKSSPHIHA5","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"UOJKSSPHIHA5OCNC","created_at":"2026-07-05T11:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"UOJKSSPH","created_at":"2026-07-05T11:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:253ff71ef467510058a1d2f2ffe6050da3b0cebaeebaec7faf97a8651783bb10","target":"graph","created_at":"2026-07-05T11:19:19Z","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/2405.11985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding. Nonetheless, most existing TEC-VQA benchmarks have focused on high-resource languages like English and Chinese. Despite pioneering works to expand multilingual QA pairs in non-text-centric VQA datasets through translation engines, the translation-based protocol encounters a substantial \"visual-textual misalignment\" problem when app","authors_text":"Can Huang, Chunhui Lin, Hao Feng, Hao Liu, Jinghui Lu, Jingqun Tang, Kuan Lu, Mohamad Fitri Faiz Bin Mahmood, Qi Liu, Shu Wei, Wanqing Li, Xiang Bai, Yangfan He, Yanjie Wang, YongJie Ye, Yuliang Liu, Zhen Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T12:35:01Z","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11985","kind":"arxiv","version":5},"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:bb0a161e3e2ba81803bbe203ba1f84c4120e3b1956b6eec849f3db2b6055bdab","target":"record","created_at":"2026-07-05T11:19:19Z","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":"24a3a16be9605a5c5e8ac0542e1b2eebf4b0ce7d2f4c46da3fe27b56c31c9806","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T12:35:01Z","title_canon_sha256":"777a20dbf4da8a4029a695ecff7601ceb5879082c8de6736d58ffdc42e02595d"},"schema_version":"1.0","source":{"id":"2405.11985","kind":"arxiv","version":5}},"canonical_sha256":"a392a949e741c1d709a20c3199b7ec676b46d955d8f0d5340083339625ae3c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a392a949e741c1d709a20c3199b7ec676b46d955d8f0d5340083339625ae3c4c","first_computed_at":"2026-07-05T11:19:19.429171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:19.429171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ioo2DTmBoBAbOJfCpmvhtPJYDhBmdW3EhYFeDvht5FqxS/zNERHGo67PxP2MWqEY0lLBsH6agF0ZqQu6LwafAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:19.429687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11985","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb0a161e3e2ba81803bbe203ba1f84c4120e3b1956b6eec849f3db2b6055bdab","sha256:253ff71ef467510058a1d2f2ffe6050da3b0cebaeebaec7faf97a8651783bb10"],"state_sha256":"547b9d3ed0548f596df747e419bfe93a7b73a1fed178e7404023b54ac10c576f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7XccvHKXAG/hQdO+dAnjraaeO2xMqHQldVm5aFX6bSLuSRjMF58fCPlHXF84TeKNek1fdCTA/Ef1hOlsFbNkAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:45:53.582941Z","bundle_sha256":"9b4f810e389a817ee7dd857f7c3fe06b96f115179a1971e70a48df3da88de57e"}}