{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PLUYNVW24VF3L7EQRKIVLRZTA","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":"cecda01a71c5e95359f9787a346e361d2adfeead4c40c2c2553c54bbfdfeb0e6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T16:05:19Z","title_canon_sha256":"6a0809b767b992024b31bb58c8f5618f745c76729e316b8ae92e930ef7244750"},"schema_version":"1.0","source":{"id":"2412.19265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19265","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19265v1","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19265","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"4PLUYNVW24VF","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"4PLUYNVW24VF3L7E","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"4PLUYNVW","created_at":"2026-07-05T09:54:33Z"}],"graph_snapshots":[{"event_id":"sha256:8a7a37e6ad94842568698cda709cab67864a29725e1b88c9dd458efa61af4020","target":"graph","created_at":"2026-07-05T09:54:33Z","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/2412.19265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient text retrieval is critical for applications such as legal document analysis, particularly in specialized contexts like Japanese legal systems. Existing retrieval methods often underperform in such domain-specific scenarios, necessitating tailored approaches. In this paper, we introduce a novel two-phase text retrieval pipeline optimized for Japanese legal datasets. Our method leverages advanced language models to achieve state-of-the-art performance, significantly improving retrieval efficiency and accuracy. To further enhance robustness and adaptability, we incorporate an ensemble m","authors_text":"Le Trung Hoang, Nguyen Van Hoang Phuc, Quang Hoang Trung","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T16:05:19Z","title":"Optimizing Multi-Stage Language Models for Effective Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19265","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:c57760f044340eb6193444897ccc3acab5d0c5286262cbb69542c3f949b8e3e3","target":"record","created_at":"2026-07-05T09:54:33Z","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":"cecda01a71c5e95359f9787a346e361d2adfeead4c40c2c2553c54bbfdfeb0e6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T16:05:19Z","title_canon_sha256":"6a0809b767b992024b31bb58c8f5618f745c76729e316b8ae92e930ef7244750"},"schema_version":"1.0","source":{"id":"2412.19265","kind":"arxiv","version":1}},"canonical_sha256":"e3d74c36b6d72a5dafe484548aae3998102a55437281d9f36af33990d2a11485","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3d74c36b6d72a5dafe484548aae3998102a55437281d9f36af33990d2a11485","first_computed_at":"2026-07-05T09:54:33.102122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:33.102122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"873JoXXKCO7BcCFrUJINjmyA89AOw8SRwRMqTRXAu9f0UJniczuONHXh0S0DzEGvsbPsYYdGho+X8aR+Ww5BAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:33.102528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c57760f044340eb6193444897ccc3acab5d0c5286262cbb69542c3f949b8e3e3","sha256:8a7a37e6ad94842568698cda709cab67864a29725e1b88c9dd458efa61af4020"],"state_sha256":"bbf0f9756f47a8a978b5c31efd8e78d89182a77ca338ca3191a839ef5c5c7489"}