{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JXIUSSWICEUTELPWNR2U35YNQG","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":"65a98e8c54c44721178abce1c2377cd51cc3a1965e2079ab7b0c97528c72efd2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-19T13:30:14Z","title_canon_sha256":"e95514533e63bdaf1f7dd6fb1b3e35ca666f9194541877c995e2d472c3ad9e87"},"schema_version":"1.0","source":{"id":"2507.14619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14619","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14619v1","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14619","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"JXIUSSWICEUT","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"JXIUSSWICEUTELPW","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"JXIUSSWI","created_at":"2026-07-05T11:40:10Z"}],"graph_snapshots":[{"event_id":"sha256:6f0195b4d8e9bc999f3eb9bbc9b42ef9ddb5818a9905e44f7b0509659c60bc92","target":"graph","created_at":"2026-07-05T11:40:10Z","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/2507.14619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) face significant challenges in specialized domains like law, where precision and domain-specific knowledge are critical. This paper presents a streamlined two-stage framework consisting of Retrieval and Re-ranking to enhance legal document retrieval efficiency and accuracy. Our approach employs a fine-tuned Bi-Encoder for rapid candidate retrieval, followed by a Cross-Encoder for precise re-ranking, both optimized through strategic negative example mining. Key innovations include the introduction of the Exist@m metric to evaluate retrieval effectiveness and the use","authors_text":"Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen, Van-Hoang Le","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-19T13:30:14Z","title":"Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14619","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:f77cb6f526232b09a1afd5db1d15ce7c909033f13d822c5640ca05e41a455451","target":"record","created_at":"2026-07-05T11:40:10Z","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":"65a98e8c54c44721178abce1c2377cd51cc3a1965e2079ab7b0c97528c72efd2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-19T13:30:14Z","title_canon_sha256":"e95514533e63bdaf1f7dd6fb1b3e35ca666f9194541877c995e2d472c3ad9e87"},"schema_version":"1.0","source":{"id":"2507.14619","kind":"arxiv","version":1}},"canonical_sha256":"4dd1494ac81129322df66c754df70d81ba1ac24be71df4767eb3b75e5821b80a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dd1494ac81129322df66c754df70d81ba1ac24be71df4767eb3b75e5821b80a","first_computed_at":"2026-07-05T11:40:10.683035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:10.683035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OBeta4b7GyTXHtsOVjytZeX6WtriILja8xybC/iZ2oy2QO45OTMKf8ewFTcDNN68eVkoc9lvoBLYdJqm4S+qAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:10.683673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f77cb6f526232b09a1afd5db1d15ce7c909033f13d822c5640ca05e41a455451","sha256:6f0195b4d8e9bc999f3eb9bbc9b42ef9ddb5818a9905e44f7b0509659c60bc92"],"state_sha256":"9613258fbb6c4331a9a717bdf6e50122f68a72ec4c7aa6297f49dee110f32632"}