{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lepard-a-large-scale-dataset-of-judges-citing","title":"LePaRD: A Large-Scale Dataset of Judges Citing Precedents","arxiv_id":"2311.09356","date":"2023-11-15","proceeding":null,"authors":["Robert Mahari","Dominik Stammbach","Elliott Ash","Alex `Sandy' Pentland"],"abstract":"We present the Legal Passage Retrieval Dataset LePaRD. LePaRD is a massive collection of U.S. federal judicial citations to precedent in context. The dataset aims to facilitate work on legal passage prediction, a challenging practice-oriented legal retrieval and reasoning task. Legal passage prediction seeks to predict relevant passages from precedential court decisions given the context of a legal argument. We extensively evaluate various retrieval approaches on LePaRD, and find that classification appears to work best. However, we note that legal precedent prediction is a difficult task, and there remains significant room for improvement. We hope that by publishing LePaRD, we will encourage others to engage with a legal NLP task that promises to help expand access to justice by reducing the burden associated with legal research. A subset of the LePaRD dataset is freely available and the whole dataset will be released upon publication.","url_abs":"https://arxiv.org/abs/2311.09356v3","url_pdf":"https://arxiv.org/pdf/2311.09356v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lepard-a-large-scale-dataset-of-judges-citing","repo_url":"https://github.com/rmahari/lepard","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.09356","atlas_url":"https://app.syntology.ai/?focus=2311.09356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09356"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rmahari/lepard","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"c30c96ac140811d7","entry":"convert_to_trec_eval","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/evaluate_run.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/evaluate_run.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c30c96ac140811d7"}},{"code_sha256_prefix":"51778abe759060d3","entry":"evaluate_epoch","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/transformer_models.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/transformer_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"51778abe759060d3"}},{"code_sha256_prefix":"4c1575fe2286cfc4","entry":"load_bm25_predictions","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/evaluate_run.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/evaluate_run.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4c1575fe2286cfc4"}},{"code_sha256_prefix":"80e5b039b964648f","entry":"load_data","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/prepare_data.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/prepare_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"80e5b039b964648f"}},{"code_sha256_prefix":"8bd2020cd2bd688b","entry":"load_datasets","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/prepare_data.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/prepare_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8bd2020cd2bd688b"}},{"code_sha256_prefix":"f8d513e48a574a19","entry":"load_np_predictions","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/evaluate_run.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/evaluate_run.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f8d513e48a574a19"}},{"code_sha256_prefix":"1c2881fd15bcd788","entry":"load_testsets","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/prepare_data.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/prepare_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1c2881fd15bcd788"}},{"code_sha256_prefix":"5ab473df7894df29","entry":"evaluate","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/transformer_models.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/transformer_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5ab473df7894df29"}},{"code_sha256_prefix":"8d953d635fe77b64","entry":"train_model","repo":"rmahari/lepard","repo_kind":"official","path":"src/model/transformer_models.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/transformer_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8d953d635fe77b64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}