{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S43EPMVJAXSPOGOYSXM3ZWTNPQ","short_pith_number":"pith:S43EPMVJ","schema_version":"1.0","canonical_sha256":"973647b2a905e4f719d895d9bcda6d7c29e603d51be2160bf984bba448372ff7","source":{"kind":"arxiv","id":"2412.19482","version":1},"attestation_state":"computed","paper":{"title":"Pre-training, Fine-tuning and Re-ranking: A Three-Stage Framework for Legal Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Cheng, Min Yang, Shiwen Ni","submitted_at":"2024-12-27T06:33:42Z","abstract_excerpt":"Legal question answering (QA) has attracted increasing attention from people seeking legal advice, which aims to retrieve the most applicable answers from a large-scale database of question-answer pairs. Previous methods mainly use a dual-encoder architecture to learn dense representations of both questions and answers. However, these methods could suffer from lacking domain knowledge and sufficient labeled training data. In this paper, we propose a three-stage (\\underline{p}re-training, \\underline{f}ine-tuning and \\underline{r}e-ranking) framework for \\underline{l}egal \\underline{QA} (called "},"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":"2412.19482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-27T06:33:42Z","cross_cats_sorted":[],"title_canon_sha256":"75226acce251702ef73f005d13013feb33a4c2b38886a0e39e0c6c68a2700c10","abstract_canon_sha256":"73ca7aa3bb011598d5da80bbec77193bf399134457c32932eaf1bee76aeb52a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:36.402925Z","signature_b64":"O2BGSJFTnZq4vRY0L5aoe7NZCSSfnLJqRzWNDjA4OT9wwlet2GSFpOGrvTjIsGNtlJ42oJkT3toyFvprhyb2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"973647b2a905e4f719d895d9bcda6d7c29e603d51be2160bf984bba448372ff7","last_reissued_at":"2026-07-05T09:54:36.402517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:36.402517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training, Fine-tuning and Re-ranking: A Three-Stage Framework for Legal Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Cheng, Min Yang, Shiwen Ni","submitted_at":"2024-12-27T06:33:42Z","abstract_excerpt":"Legal question answering (QA) has attracted increasing attention from people seeking legal advice, which aims to retrieve the most applicable answers from a large-scale database of question-answer pairs. Previous methods mainly use a dual-encoder architecture to learn dense representations of both questions and answers. However, these methods could suffer from lacking domain knowledge and sufficient labeled training data. In this paper, we propose a three-stage (\\underline{p}re-training, \\underline{f}ine-tuning and \\underline{r}e-ranking) framework for \\underline{l}egal \\underline{QA} (called "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19482","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/2412.19482/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":"2412.19482","created_at":"2026-07-05T09:54:36.402573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19482v1","created_at":"2026-07-05T09:54:36.402573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19482","created_at":"2026-07-05T09:54:36.402573+00:00"},{"alias_kind":"pith_short_12","alias_value":"S43EPMVJAXSP","created_at":"2026-07-05T09:54:36.402573+00:00"},{"alias_kind":"pith_short_16","alias_value":"S43EPMVJAXSPOGOY","created_at":"2026-07-05T09:54:36.402573+00:00"},{"alias_kind":"pith_short_8","alias_value":"S43EPMVJ","created_at":"2026-07-05T09:54:36.402573+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/S43EPMVJAXSPOGOYSXM3ZWTNPQ","json":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ.json","graph_json":"https://pith.science/api/pith-number/S43EPMVJAXSPOGOYSXM3ZWTNPQ/graph.json","events_json":"https://pith.science/api/pith-number/S43EPMVJAXSPOGOYSXM3ZWTNPQ/events.json","paper":"https://pith.science/paper/S43EPMVJ"},"agent_actions":{"view_html":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ","download_json":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ.json","view_paper":"https://pith.science/paper/S43EPMVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19482&json=true","fetch_graph":"https://pith.science/api/pith-number/S43EPMVJAXSPOGOYSXM3ZWTNPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/S43EPMVJAXSPOGOYSXM3ZWTNPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ/action/storage_attestation","attest_author":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ/action/author_attestation","sign_citation":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ/action/citation_signature","submit_replication":"https://pith.science/pith/S43EPMVJAXSPOGOYSXM3ZWTNPQ/action/replication_record"}},"created_at":"2026-07-05T09:54:36.402573+00:00","updated_at":"2026-07-05T09:54:36.402573+00:00"}