{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O7427VSTD2MNJKQSFLA2VNJ6S4","short_pith_number":"pith:O7427VST","schema_version":"1.0","canonical_sha256":"77f9afd6531e98d4aa122ac1aab53e9701a975b4112eb774c29eb43850083072","source":{"kind":"arxiv","id":"2507.19995","version":1},"attestation_state":"computed","paper":{"title":"VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ha-Thanh Nguyen, Hoang-Trung Nguyen, Tan-Minh Nguyen, Thi-Hai-Yen Vuong, Trong-Khoi Dao, Xuan-Hieu Phan","submitted_at":"2025-07-26T16:26:50Z","abstract_excerpt":"The advent of large language models (LLMs) has led to significant achievements in various domains, including legal text processing. Leveraging LLMs for legal tasks is a natural evolution and an increasingly compelling choice. However, their capabilities are often portrayed as greater than they truly are. Despite the progress, we are still far from the ultimate goal of fully automating legal tasks using artificial intelligence (AI) and natural language processing (NLP). Moreover, legal systems are deeply domain-specific and exhibit substantial variation across different countries and languages."},"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":"2507.19995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T16:26:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ab848697428ec4704eb9def91961ba79235b5a5df986a1b129ad3c00d46d329","abstract_canon_sha256":"69f3c6b1953f42c120b981a7c5197f1b53537ef0db53aa94bf32c32139509b31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:46.212976Z","signature_b64":"bVpiDN42LyDn01kfUPIVEFItBOt3WzFS5uyL4LIxnVViQn8sbHdOXMnJtrJTNN3W/jP195Jx8MoM5SXv0EsRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77f9afd6531e98d4aa122ac1aab53e9701a975b4112eb774c29eb43850083072","last_reissued_at":"2026-07-05T11:43:46.212512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:46.212512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ha-Thanh Nguyen, Hoang-Trung Nguyen, Tan-Minh Nguyen, Thi-Hai-Yen Vuong, Trong-Khoi Dao, Xuan-Hieu Phan","submitted_at":"2025-07-26T16:26:50Z","abstract_excerpt":"The advent of large language models (LLMs) has led to significant achievements in various domains, including legal text processing. Leveraging LLMs for legal tasks is a natural evolution and an increasingly compelling choice. However, their capabilities are often portrayed as greater than they truly are. Despite the progress, we are still far from the ultimate goal of fully automating legal tasks using artificial intelligence (AI) and natural language processing (NLP). Moreover, legal systems are deeply domain-specific and exhibit substantial variation across different countries and languages."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19995","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/2507.19995/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":"2507.19995","created_at":"2026-07-05T11:43:46.212580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19995v1","created_at":"2026-07-05T11:43:46.212580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19995","created_at":"2026-07-05T11:43:46.212580+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7427VSTD2MN","created_at":"2026-07-05T11:43:46.212580+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7427VSTD2MNJKQS","created_at":"2026-07-05T11:43:46.212580+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7427VST","created_at":"2026-07-05T11:43:46.212580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16270","citing_title":"From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4","json":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4.json","graph_json":"https://pith.science/api/pith-number/O7427VSTD2MNJKQSFLA2VNJ6S4/graph.json","events_json":"https://pith.science/api/pith-number/O7427VSTD2MNJKQSFLA2VNJ6S4/events.json","paper":"https://pith.science/paper/O7427VST"},"agent_actions":{"view_html":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4","download_json":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4.json","view_paper":"https://pith.science/paper/O7427VST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19995&json=true","fetch_graph":"https://pith.science/api/pith-number/O7427VSTD2MNJKQSFLA2VNJ6S4/graph.json","fetch_events":"https://pith.science/api/pith-number/O7427VSTD2MNJKQSFLA2VNJ6S4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4/action/storage_attestation","attest_author":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4/action/author_attestation","sign_citation":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4/action/citation_signature","submit_replication":"https://pith.science/pith/O7427VSTD2MNJKQSFLA2VNJ6S4/action/replication_record"}},"created_at":"2026-07-05T11:43:46.212580+00:00","updated_at":"2026-07-05T11:43:46.212580+00:00"}