{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:76FQ54XW4GXUSZB2LST3HTERSH","short_pith_number":"pith:76FQ54XW","schema_version":"1.0","canonical_sha256":"ff8b0ef2f6e1af49643a5ca7b3cc9191c3b37feb05741a08ce23a0f1abee0dcc","source":{"kind":"arxiv","id":"2203.07742","version":1},"attestation_state":"computed","paper":{"title":"ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dung Nguyen Manh, Long Tran Quoc, Phi Nguyen Van, Quan Nguyen Minh, Tung Cao Hoang","submitted_at":"2022-03-15T09:22:04Z","abstract_excerpt":"Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English. Therefore, their performance in low-resource languages is still a significant problem due to the absence of a standard dataset and evaluation policy. To address this problem, we proposed ViWOZ, a fully-annotated Vietnamese task-oriented dialogue dataset. ViWOZ is the first multi-turn, multi-domain tasked oriented dataset in Vietnamese, a low-resource language. The dataset consists of a total of 5,000 dialogues, including 60,946 fully an"},"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":"2203.07742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-15T09:22:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bafcc2181d7f7b487a63e391853924cfef5ef5a11b843e0e39218dcdc62c6af","abstract_canon_sha256":"57061da35a2b3cb503be3edd481374b17996169b8645260a8d7aeaf8139177e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:22.222342Z","signature_b64":"vGTxXmMjo2yA6g29hONgwQidYKHphYDaGjZKtEVmaWvMbxGGxTw3EdqohEksjb2tflwuP3sxc2107WcHDFDwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff8b0ef2f6e1af49643a5ca7b3cc9191c3b37feb05741a08ce23a0f1abee0dcc","last_reissued_at":"2026-07-05T04:05:22.221879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:22.221879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dung Nguyen Manh, Long Tran Quoc, Phi Nguyen Van, Quan Nguyen Minh, Tung Cao Hoang","submitted_at":"2022-03-15T09:22:04Z","abstract_excerpt":"Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English. Therefore, their performance in low-resource languages is still a significant problem due to the absence of a standard dataset and evaluation policy. To address this problem, we proposed ViWOZ, a fully-annotated Vietnamese task-oriented dialogue dataset. ViWOZ is the first multi-turn, multi-domain tasked oriented dataset in Vietnamese, a low-resource language. The dataset consists of a total of 5,000 dialogues, including 60,946 fully an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07742","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/2203.07742/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":"2203.07742","created_at":"2026-07-05T04:05:22.221935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07742v1","created_at":"2026-07-05T04:05:22.221935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07742","created_at":"2026-07-05T04:05:22.221935+00:00"},{"alias_kind":"pith_short_12","alias_value":"76FQ54XW4GXU","created_at":"2026-07-05T04:05:22.221935+00:00"},{"alias_kind":"pith_short_16","alias_value":"76FQ54XW4GXUSZB2","created_at":"2026-07-05T04:05:22.221935+00:00"},{"alias_kind":"pith_short_8","alias_value":"76FQ54XW","created_at":"2026-07-05T04:05:22.221935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07069","citing_title":"SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH","json":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH.json","graph_json":"https://pith.science/api/pith-number/76FQ54XW4GXUSZB2LST3HTERSH/graph.json","events_json":"https://pith.science/api/pith-number/76FQ54XW4GXUSZB2LST3HTERSH/events.json","paper":"https://pith.science/paper/76FQ54XW"},"agent_actions":{"view_html":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH","download_json":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH.json","view_paper":"https://pith.science/paper/76FQ54XW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07742&json=true","fetch_graph":"https://pith.science/api/pith-number/76FQ54XW4GXUSZB2LST3HTERSH/graph.json","fetch_events":"https://pith.science/api/pith-number/76FQ54XW4GXUSZB2LST3HTERSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH/action/storage_attestation","attest_author":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH/action/author_attestation","sign_citation":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH/action/citation_signature","submit_replication":"https://pith.science/pith/76FQ54XW4GXUSZB2LST3HTERSH/action/replication_record"}},"created_at":"2026-07-05T04:05:22.221935+00:00","updated_at":"2026-07-05T04:05:22.221935+00:00"}