{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7L2G7LTG4QNMDMNPSOUBRBHCLX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a11d12addfe4cd59eabb7a872fb9ff30872c6bb2609c16c0bc5dc3c401e50c49","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-01T03:28:26Z","title_canon_sha256":"748c2d0bd1026dcdc2582ca622cd0aef91af16f8d43e4ae3f39479e434cb470e"},"schema_version":"1.0","source":{"id":"2412.00657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00657","created_at":"2026-07-05T09:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00657v1","created_at":"2026-07-05T09:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00657","created_at":"2026-07-05T09:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"7L2G7LTG4QNM","created_at":"2026-07-05T09:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"7L2G7LTG4QNMDMNP","created_at":"2026-07-05T09:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"7L2G7LTG","created_at":"2026-07-05T09:42:44Z"}],"graph_snapshots":[{"event_id":"sha256:7500bddb9599a4191162c4f3ff04a6098d24362fb785460681fb420b37c56caf","target":"graph","created_at":"2026-07-05T09:42:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.00657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"An Nguyen Dai, Hieu Nguyen Doan, Sang Dinh Viet, Son Pham Tien","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-01T03:28:26Z","title":"Improving Vietnamese Legal Document Retrieval using Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00657","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c475f6cbc3a8316529d05c8a4f4a457114f6fe04dd5aeb82973751691ed4c4fa","target":"record","created_at":"2026-07-05T09:42:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a11d12addfe4cd59eabb7a872fb9ff30872c6bb2609c16c0bc5dc3c401e50c49","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-01T03:28:26Z","title_canon_sha256":"748c2d0bd1026dcdc2582ca622cd0aef91af16f8d43e4ae3f39479e434cb470e"},"schema_version":"1.0","source":{"id":"2412.00657","kind":"arxiv","version":1}},"canonical_sha256":"faf46fae66e41ac1b1af93a81884e25dd671cc49c3b28176746a4a0207d2b9db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faf46fae66e41ac1b1af93a81884e25dd671cc49c3b28176746a4a0207d2b9db","first_computed_at":"2026-07-05T09:42:44.834886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:44.834886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eo9rvR2wgV8MLr2xIxjcH4T6IGrzUAPHcFyq9LioKLEqkEdktRuSH7rjtDBb3gUrcFunx5cl68sixi9yjxw4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:44.835369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c475f6cbc3a8316529d05c8a4f4a457114f6fe04dd5aeb82973751691ed4c4fa","sha256:7500bddb9599a4191162c4f3ff04a6098d24362fb785460681fb420b37c56caf"],"state_sha256":"e9f25436fa218c71079912b36e6a620c8bfe89bd9ff3d7497c5f4394ae3055f8"}