{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7L2G7LTG4QNMDMNPSOUBRBHCLX","short_pith_number":"pith:7L2G7LTG","schema_version":"1.0","canonical_sha256":"faf46fae66e41ac1b1af93a81884e25dd671cc49c3b28176746a4a0207d2b9db","source":{"kind":"arxiv","id":"2412.00657","version":1},"attestation_state":"computed","paper":{"title":"Improving Vietnamese Legal Document Retrieval using Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"An Nguyen Dai, Hieu Nguyen Doan, Sang Dinh Viet, Son Pham Tien","submitted_at":"2024-12-01T03:28:26Z","abstract_excerpt":"In the field of legal information retrieval, effective embedding-based models are essential for accurate question-answering systems. However, the scarcity of large annotated datasets poses a significant challenge, particularly for Vietnamese legal texts. To address this issue, we propose a novel approach that leverages large language models to generate high-quality, diverse synthetic queries for Vietnamese legal passages. This synthetic data is then used to pre-train retrieval models, specifically bi-encoder and ColBERT, which are further fine-tuned using contrastive loss with mined hard negat"},"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":"2412.00657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-01T03:28:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"748c2d0bd1026dcdc2582ca622cd0aef91af16f8d43e4ae3f39479e434cb470e","abstract_canon_sha256":"a11d12addfe4cd59eabb7a872fb9ff30872c6bb2609c16c0bc5dc3c401e50c49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:44.835369Z","signature_b64":"Eo9rvR2wgV8MLr2xIxjcH4T6IGrzUAPHcFyq9LioKLEqkEdktRuSH7rjtDBb3gUrcFunx5cl68sixi9yjxw4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faf46fae66e41ac1b1af93a81884e25dd671cc49c3b28176746a4a0207d2b9db","last_reissued_at":"2026-07-05T09:42:44.834886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:44.834886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Vietnamese Legal Document Retrieval using Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"An Nguyen Dai, Hieu Nguyen Doan, Sang Dinh Viet, Son Pham Tien","submitted_at":"2024-12-01T03:28:26Z","abstract_excerpt":"In the field of legal information retrieval, effective embedding-based models are essential for accurate question-answering systems. However, the scarcity of large annotated datasets poses a significant challenge, particularly for Vietnamese legal texts. To address this issue, we propose a novel approach that leverages large language models to generate high-quality, diverse synthetic queries for Vietnamese legal passages. This synthetic data is then used to pre-train retrieval models, specifically bi-encoder and ColBERT, which are further fine-tuned using contrastive loss with mined hard negat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00657","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/2412.00657/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":"2412.00657","created_at":"2026-07-05T09:42:44.834947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00657v1","created_at":"2026-07-05T09:42:44.834947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00657","created_at":"2026-07-05T09:42:44.834947+00:00"},{"alias_kind":"pith_short_12","alias_value":"7L2G7LTG4QNM","created_at":"2026-07-05T09:42:44.834947+00:00"},{"alias_kind":"pith_short_16","alias_value":"7L2G7LTG4QNMDMNP","created_at":"2026-07-05T09:42:44.834947+00:00"},{"alias_kind":"pith_short_8","alias_value":"7L2G7LTG","created_at":"2026-07-05T09:42:44.834947+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/7L2G7LTG4QNMDMNPSOUBRBHCLX","json":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX.json","graph_json":"https://pith.science/api/pith-number/7L2G7LTG4QNMDMNPSOUBRBHCLX/graph.json","events_json":"https://pith.science/api/pith-number/7L2G7LTG4QNMDMNPSOUBRBHCLX/events.json","paper":"https://pith.science/paper/7L2G7LTG"},"agent_actions":{"view_html":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX","download_json":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX.json","view_paper":"https://pith.science/paper/7L2G7LTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00657&json=true","fetch_graph":"https://pith.science/api/pith-number/7L2G7LTG4QNMDMNPSOUBRBHCLX/graph.json","fetch_events":"https://pith.science/api/pith-number/7L2G7LTG4QNMDMNPSOUBRBHCLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX/action/storage_attestation","attest_author":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX/action/author_attestation","sign_citation":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX/action/citation_signature","submit_replication":"https://pith.science/pith/7L2G7LTG4QNMDMNPSOUBRBHCLX/action/replication_record"}},"created_at":"2026-07-05T09:42:44.834947+00:00","updated_at":"2026-07-05T09:42:44.834947+00:00"}