{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IDD46DHPG75BYTPAOG5TR5CRK4","short_pith_number":"pith:IDD46DHP","schema_version":"1.0","canonical_sha256":"40c7cf0cef37fa1c4de071bb38f451573b07d3513831d89434926a11dfff85b9","source":{"kind":"arxiv","id":"2009.14725","version":3},"attestation_state":"computed","paper":{"title":"A Vietnamese Dataset for Evaluating Machine Reading Comprehension","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Gia-Tuan Nguyen, Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen","submitted_at":"2020-09-30T15:06:56Z","abstract_excerpt":"Over 97 million people speak Vietnamese as their native language in the world. However, there are few research studies on machine reading comprehension (MRC) for Vietnamese, the task of understanding a text and answering questions related to it. Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models. This dataset comprises over 23,000 human-generated question-answer pairs based on 5,109 passages of 174 Vietnamese articles from Wikipedia. In particul"},"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":"2009.14725","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-09-30T15:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"9b99b1e20d44340a39d3fce10ae77f6e6d1aadf49948e0ba8caf681da5532d70","abstract_canon_sha256":"ad3fb52d89bd7441abcd6eec0b8370436f7ad1f424d609a50efcc9fb9eba1bbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:55.096288Z","signature_b64":"NLD9LywFsKb48gnTi77+OqozKDh009PPiGTgmZhoacE+LkC6MdwZyR/9wB9WUYCGA/kRgQL7evYpJuu1T0NpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40c7cf0cef37fa1c4de071bb38f451573b07d3513831d89434926a11dfff85b9","last_reissued_at":"2026-07-05T01:49:55.095802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:55.095802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Vietnamese Dataset for Evaluating Machine Reading Comprehension","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Gia-Tuan Nguyen, Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen","submitted_at":"2020-09-30T15:06:56Z","abstract_excerpt":"Over 97 million people speak Vietnamese as their native language in the world. However, there are few research studies on machine reading comprehension (MRC) for Vietnamese, the task of understanding a text and answering questions related to it. Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models. This dataset comprises over 23,000 human-generated question-answer pairs based on 5,109 passages of 174 Vietnamese articles from Wikipedia. In particul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14725","kind":"arxiv","version":3},"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/2009.14725/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":"2009.14725","created_at":"2026-07-05T01:49:55.095862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.14725v3","created_at":"2026-07-05T01:49:55.095862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14725","created_at":"2026-07-05T01:49:55.095862+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDD46DHPG75B","created_at":"2026-07-05T01:49:55.095862+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDD46DHPG75BYTPA","created_at":"2026-07-05T01:49:55.095862+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDD46DHP","created_at":"2026-07-05T01:49:55.095862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08621","citing_title":"ViBidirectionMT-Eval: Machine Translation for Vietnamese-Chinese and Vietnamese-Lao language pair","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4","json":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4.json","graph_json":"https://pith.science/api/pith-number/IDD46DHPG75BYTPAOG5TR5CRK4/graph.json","events_json":"https://pith.science/api/pith-number/IDD46DHPG75BYTPAOG5TR5CRK4/events.json","paper":"https://pith.science/paper/IDD46DHP"},"agent_actions":{"view_html":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4","download_json":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4.json","view_paper":"https://pith.science/paper/IDD46DHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.14725&json=true","fetch_graph":"https://pith.science/api/pith-number/IDD46DHPG75BYTPAOG5TR5CRK4/graph.json","fetch_events":"https://pith.science/api/pith-number/IDD46DHPG75BYTPAOG5TR5CRK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4/action/storage_attestation","attest_author":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4/action/author_attestation","sign_citation":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4/action/citation_signature","submit_replication":"https://pith.science/pith/IDD46DHPG75BYTPAOG5TR5CRK4/action/replication_record"}},"created_at":"2026-07-05T01:49:55.095862+00:00","updated_at":"2026-07-05T01:49:55.095862+00:00"}