{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OKVBWV5GGYRUFP2JNFORSCUUGU","short_pith_number":"pith:OKVBWV5G","schema_version":"1.0","canonical_sha256":"72aa1b57a6362342bf49695d190a943527b8bfc7cd5bc8e5362297c141087dfa","source":{"kind":"arxiv","id":"2508.19944","version":2},"attestation_state":"computed","paper":{"title":"KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gisang Lee, Hyunjun Eun, Minseo Kim, Seonuk Kim, Taebaek Hwang","submitted_at":"2025-08-27T15:01:02Z","abstract_excerpt":"Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models (VLMs), given the complexity and diversity of real-world scenarios. To address this challenge, text-rich Visual Question Answering (VQA) datasets and benchmarks have emerged for high-resource languages like English. However, a critical gap persists for low-resource languages such as Korean, where the lack of comprehensive benchmarks hinders robust model evaluation and comparison. To bridge this gap, we introduce KRETA, a benchmark for Korean Reading and rEasoning in Text-rich V"},"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":"2508.19944","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T15:01:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ea83cd48f6821fb786460755c84783af02dc98db4787909b55008330d535e362","abstract_canon_sha256":"94dab71d8eef4934b30eeb3fc9184cac923584263fafad28ba98d2492876ced0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:07.242028Z","signature_b64":"M3pLPJ7wELDWD65aMGs82x/+l5JGrzVN9Swnqdn31CYjtjrx5aCqCjGuD93/1S36jxJTC6sMkxRxYMSP2B/cAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72aa1b57a6362342bf49695d190a943527b8bfc7cd5bc8e5362297c141087dfa","last_reissued_at":"2026-07-05T12:02:07.241555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:07.241555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gisang Lee, Hyunjun Eun, Minseo Kim, Seonuk Kim, Taebaek Hwang","submitted_at":"2025-08-27T15:01:02Z","abstract_excerpt":"Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models (VLMs), given the complexity and diversity of real-world scenarios. To address this challenge, text-rich Visual Question Answering (VQA) datasets and benchmarks have emerged for high-resource languages like English. However, a critical gap persists for low-resource languages such as Korean, where the lack of comprehensive benchmarks hinders robust model evaluation and comparison. To bridge this gap, we introduce KRETA, a benchmark for Korean Reading and rEasoning in Text-rich V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19944","kind":"arxiv","version":2},"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/2508.19944/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":"2508.19944","created_at":"2026-07-05T12:02:07.241619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19944v2","created_at":"2026-07-05T12:02:07.241619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19944","created_at":"2026-07-05T12:02:07.241619+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKVBWV5GGYRU","created_at":"2026-07-05T12:02:07.241619+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKVBWV5GGYRUFP2J","created_at":"2026-07-05T12:02:07.241619+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKVBWV5G","created_at":"2026-07-05T12:02:07.241619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU","json":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU.json","graph_json":"https://pith.science/api/pith-number/OKVBWV5GGYRUFP2JNFORSCUUGU/graph.json","events_json":"https://pith.science/api/pith-number/OKVBWV5GGYRUFP2JNFORSCUUGU/events.json","paper":"https://pith.science/paper/OKVBWV5G"},"agent_actions":{"view_html":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU","download_json":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU.json","view_paper":"https://pith.science/paper/OKVBWV5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19944&json=true","fetch_graph":"https://pith.science/api/pith-number/OKVBWV5GGYRUFP2JNFORSCUUGU/graph.json","fetch_events":"https://pith.science/api/pith-number/OKVBWV5GGYRUFP2JNFORSCUUGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU/action/storage_attestation","attest_author":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU/action/author_attestation","sign_citation":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU/action/citation_signature","submit_replication":"https://pith.science/pith/OKVBWV5GGYRUFP2JNFORSCUUGU/action/replication_record"}},"created_at":"2026-07-05T12:02:07.241619+00:00","updated_at":"2026-07-05T12:02:07.241619+00:00"}