{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SBXSA5X4WM2QPZKF2BQFTVGHCT","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":"efc4ac56c4cea1ec35f763f5ae79dcfb6f639cdf12129ea62f6cff1dddfbb263","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:48:04Z","title_canon_sha256":"da62dd77d7400e5e306ec89df0eafd4b91268a6d22d92e78a440ed9a0c581ac8"},"schema_version":"1.0","source":{"id":"2412.17787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17787","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17787v1","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17787","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"pith_short_12","alias_value":"SBXSA5X4WM2Q","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"pith_short_16","alias_value":"SBXSA5X4WM2QPZKF","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"pith_short_8","alias_value":"SBXSA5X4","created_at":"2026-07-05T09:53:27Z"}],"graph_snapshots":[{"event_id":"sha256:7d2616508427344f9e4c0d8d06f031c8ef54e75974576576b37ff5670c831124","target":"graph","created_at":"2026-07-05T09:53:27Z","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/2412.17787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Large Vision-Language Models (LVLMs) have shown promising reasoning capabilities on text-rich images from charts, tables, and documents. However, the abundant text within such images may increase the model's sensitivity to language. This raises the need to evaluate LVLM performance on cross-lingual text-rich visual inputs, where the language in the image differs from the language of the instructions. To address this, we introduce XT-VQA (Cross-Lingual Text-Rich Visual Question Answering), a benchmark designed to assess how LVLMs handle language inconsistency between image text and quest","authors_text":"Bing Qin, Dandan Tu, Duyu Tang, Jihao Wu, Mengkang Hu, Minghui Liao, Ruihan Chen, Weihong Zhong, Xiachong Feng, Xiaocheng Feng, Xinmiao Yu, Ya-Qi Yu, Yun Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:48:04Z","title":"Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17787","kind":"arxiv","version":1},"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":"sha256:2b7164a87f245f0550d006d3df68356ab3d9a2563653554c6c3b6ad221a56908","target":"record","created_at":"2026-07-05T09:53:27Z","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":"efc4ac56c4cea1ec35f763f5ae79dcfb6f639cdf12129ea62f6cff1dddfbb263","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:48:04Z","title_canon_sha256":"da62dd77d7400e5e306ec89df0eafd4b91268a6d22d92e78a440ed9a0c581ac8"},"schema_version":"1.0","source":{"id":"2412.17787","kind":"arxiv","version":1}},"canonical_sha256":"906f2076fcb33507e545d06059d4c714f953882c755e61cce7acfd65f036484f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"906f2076fcb33507e545d06059d4c714f953882c755e61cce7acfd65f036484f","first_computed_at":"2026-07-05T09:53:27.327831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:27.327831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fvCX19tNj++DiXdXWSu7Q/ZybT2JEBEHuDylMlhRbZliYnF+xvtL8fglGegLiLBMr0is0C6urp0uiwlVBFqMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:27.328337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b7164a87f245f0550d006d3df68356ab3d9a2563653554c6c3b6ad221a56908","sha256:7d2616508427344f9e4c0d8d06f031c8ef54e75974576576b37ff5670c831124"],"state_sha256":"6fd006b30e04c9bea7ffdba71f2608de2605e381a2b36b5cbe18a7fe5d325823"}