{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FWL6DBQBZXRRGCSPMMV6YFAJ2D","short_pith_number":"pith:FWL6DBQB","schema_version":"1.0","canonical_sha256":"2d97e18601cde3130a4f632bec1409d0f4b1e5c1ce9943cce76f207094b6e2d7","source":{"kind":"arxiv","id":"2502.19202","version":2},"attestation_state":"computed","paper":{"title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kiet Van Nguyen, Nghia Hieu Nguyen, Thanh-Phong Le, Trung Le Chi Phan","submitted_at":"2025-02-26T15:09:28Z","abstract_excerpt":"Document Visual Question Answering (Document VQA) challenges multimodal systems to holistically handle textual, layout, and visual modalities to provide appropriate answers. Document VQA has gained popularity in recent years due to the increasing amount of documents and the high demand for digitization. Nonetheless, most of document VQA datasets are developed in high-resource languages such as English. In this paper, we present ReceiptVQA (\\textbf{Receipt} \\textbf{V}isual \\textbf{Q}uestion \\textbf{A}nswering), the initial large-scale document VQA dataset in Vietnamese dedicated to receipts, a "},"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":"2502.19202","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T15:09:28Z","cross_cats_sorted":[],"title_canon_sha256":"7b202b9201bfcbb018696449bc8a1aec6a468e693db5e6d928256c54b3d90d3a","abstract_canon_sha256":"c5e3101bc10f8ba17ee58d03193c32d7deed46ecb993f27cc09c9d604b38c5a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:14.791667Z","signature_b64":"A6Ax+jzYEpPfrk3u/sAO05dJ/h+Nbp4ZrT6QB6PA81yY0sajQHHRaAem4YveWfDtN2TA5Dq0t5sAkd5rgQwWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d97e18601cde3130a4f632bec1409d0f4b1e5c1ce9943cce76f207094b6e2d7","last_reissued_at":"2026-07-05T10:26:14.791155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:14.791155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kiet Van Nguyen, Nghia Hieu Nguyen, Thanh-Phong Le, Trung Le Chi Phan","submitted_at":"2025-02-26T15:09:28Z","abstract_excerpt":"Document Visual Question Answering (Document VQA) challenges multimodal systems to holistically handle textual, layout, and visual modalities to provide appropriate answers. Document VQA has gained popularity in recent years due to the increasing amount of documents and the high demand for digitization. Nonetheless, most of document VQA datasets are developed in high-resource languages such as English. In this paper, we present ReceiptVQA (\\textbf{Receipt} \\textbf{V}isual \\textbf{Q}uestion \\textbf{A}nswering), the initial large-scale document VQA dataset in Vietnamese dedicated to receipts, a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19202","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/2502.19202/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":"2502.19202","created_at":"2026-07-05T10:26:14.791235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19202v2","created_at":"2026-07-05T10:26:14.791235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19202","created_at":"2026-07-05T10:26:14.791235+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWL6DBQBZXRR","created_at":"2026-07-05T10:26:14.791235+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWL6DBQBZXRRGCSP","created_at":"2026-07-05T10:26:14.791235+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWL6DBQB","created_at":"2026-07-05T10:26:14.791235+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/FWL6DBQBZXRRGCSPMMV6YFAJ2D","json":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D.json","graph_json":"https://pith.science/api/pith-number/FWL6DBQBZXRRGCSPMMV6YFAJ2D/graph.json","events_json":"https://pith.science/api/pith-number/FWL6DBQBZXRRGCSPMMV6YFAJ2D/events.json","paper":"https://pith.science/paper/FWL6DBQB"},"agent_actions":{"view_html":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D","download_json":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D.json","view_paper":"https://pith.science/paper/FWL6DBQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19202&json=true","fetch_graph":"https://pith.science/api/pith-number/FWL6DBQBZXRRGCSPMMV6YFAJ2D/graph.json","fetch_events":"https://pith.science/api/pith-number/FWL6DBQBZXRRGCSPMMV6YFAJ2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D/action/storage_attestation","attest_author":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D/action/author_attestation","sign_citation":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D/action/citation_signature","submit_replication":"https://pith.science/pith/FWL6DBQBZXRRGCSPMMV6YFAJ2D/action/replication_record"}},"created_at":"2026-07-05T10:26:14.791235+00:00","updated_at":"2026-07-05T10:26:14.791235+00:00"}