{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M63DQ6B5WYNMRVQ3WASHAUDNYP","short_pith_number":"pith:M63DQ6B5","schema_version":"1.0","canonical_sha256":"67b638783db61ac8d61bb02470506dc3e67883b3d9cd869a1903dd9a7f0ee730","source":{"kind":"arxiv","id":"2305.12199","version":1},"attestation_state":"computed","paper":{"title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bac-Bien Ngo, Hong-Phuoc Nguyen, Ngoc-Bich Le, The-Duy Vo, Thi-My-Thanh Nguyen, Van-Tien Nguyen, Xuan-Dung Phan, Xuan-Quy Dao","submitted_at":"2023-05-20T14:13:08Z","abstract_excerpt":"The VNHSGE (VietNamese High School Graduation Examination) dataset, developed exclusively for evaluating large language models (LLMs), is introduced in this article. The dataset, which covers nine subjects, was generated from the Vietnamese National High School Graduation Examination and comparable tests. 300 literary essays have been included, and there are over 19,000 multiple-choice questions on a range of topics. The dataset assesses LLMs in multitasking situations such as question answering, text generation, reading comprehension, visual question answering, and more by including both text"},"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":"2305.12199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T14:13:08Z","cross_cats_sorted":[],"title_canon_sha256":"258a0ed7a541d060c38d2419fd24a4ff85f8227463ba3ceb71c82f2870565929","abstract_canon_sha256":"1c84757844a3f5dabb5877decbbcc7c890bf001a887c7c4e07d226ccbcb950b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:33.257505Z","signature_b64":"CmDSmHzDUppvs28pFPssc7lefbhFD8dzBpITJ4PCOJ3RIs/k71b9TsT7fnC6IPGhlaIpQ2QBRIaA6c0KuXP0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67b638783db61ac8d61bb02470506dc3e67883b3d9cd869a1903dd9a7f0ee730","last_reissued_at":"2026-07-05T06:27:33.256983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:33.256983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bac-Bien Ngo, Hong-Phuoc Nguyen, Ngoc-Bich Le, The-Duy Vo, Thi-My-Thanh Nguyen, Van-Tien Nguyen, Xuan-Dung Phan, Xuan-Quy Dao","submitted_at":"2023-05-20T14:13:08Z","abstract_excerpt":"The VNHSGE (VietNamese High School Graduation Examination) dataset, developed exclusively for evaluating large language models (LLMs), is introduced in this article. The dataset, which covers nine subjects, was generated from the Vietnamese National High School Graduation Examination and comparable tests. 300 literary essays have been included, and there are over 19,000 multiple-choice questions on a range of topics. The dataset assesses LLMs in multitasking situations such as question answering, text generation, reading comprehension, visual question answering, and more by including both text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12199","kind":"arxiv","version":1},"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/2305.12199/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":"2305.12199","created_at":"2026-07-05T06:27:33.257053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12199v1","created_at":"2026-07-05T06:27:33.257053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12199","created_at":"2026-07-05T06:27:33.257053+00:00"},{"alias_kind":"pith_short_12","alias_value":"M63DQ6B5WYNM","created_at":"2026-07-05T06:27:33.257053+00:00"},{"alias_kind":"pith_short_16","alias_value":"M63DQ6B5WYNMRVQ3","created_at":"2026-07-05T06:27:33.257053+00:00"},{"alias_kind":"pith_short_8","alias_value":"M63DQ6B5","created_at":"2026-07-05T06:27:33.257053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28647","citing_title":"ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP","json":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP.json","graph_json":"https://pith.science/api/pith-number/M63DQ6B5WYNMRVQ3WASHAUDNYP/graph.json","events_json":"https://pith.science/api/pith-number/M63DQ6B5WYNMRVQ3WASHAUDNYP/events.json","paper":"https://pith.science/paper/M63DQ6B5"},"agent_actions":{"view_html":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP","download_json":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP.json","view_paper":"https://pith.science/paper/M63DQ6B5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12199&json=true","fetch_graph":"https://pith.science/api/pith-number/M63DQ6B5WYNMRVQ3WASHAUDNYP/graph.json","fetch_events":"https://pith.science/api/pith-number/M63DQ6B5WYNMRVQ3WASHAUDNYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP/action/storage_attestation","attest_author":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP/action/author_attestation","sign_citation":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP/action/citation_signature","submit_replication":"https://pith.science/pith/M63DQ6B5WYNMRVQ3WASHAUDNYP/action/replication_record"}},"created_at":"2026-07-05T06:27:33.257053+00:00","updated_at":"2026-07-05T06:27:33.257053+00:00"}