{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DIZTC55A5AD5LW7FGWD6OQWFUV","short_pith_number":"pith:DIZTC55A","schema_version":"1.0","canonical_sha256":"1a333177a0e807d5dbe53587e742c5a56060c5b14d9ba91ca6e5c4a921ae7550","source":{"kind":"arxiv","id":"2410.08731","version":1},"attestation_state":"computed","paper":{"title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eunkyung Choi, Hai Jin Park, Jinhwan Choi, Wonseok Hwang, YeEun Kim, Young Rok Choi","submitted_at":"2024-10-11T11:41:02Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages other than English. This underscores the need for careful evaluation of LLMs within each legal system before application. Here, we introduce KBL, a benchmark for assessing the Korean legal language understanding of LLMs, consisting of (1) 7 legal knowledge tasks (510 examples), (2) 4 legal reasoning tasks (288 examples), and (3) the Korean bar exam (4 domains, "},"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":"2410.08731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T11:41:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1243b2575554aff50a5a27ada1271089d995b6bd68e0845f1cc82272b7ff8974","abstract_canon_sha256":"9973d5bd01c967b460344b77c0c4ff65d301d822d08d7f42a8c422bb1221b97b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:16.798407Z","signature_b64":"MFeuWTobi4U3F8QcYlnLSltQIA9GHXBZ6NSFsQubqdt4qQHBcSQmAhwBch+E6QiPZ+XOZVWE96kz9jGjC4aVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a333177a0e807d5dbe53587e742c5a56060c5b14d9ba91ca6e5c4a921ae7550","last_reissued_at":"2026-07-05T09:19:16.798004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:16.798004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eunkyung Choi, Hai Jin Park, Jinhwan Choi, Wonseok Hwang, YeEun Kim, Young Rok Choi","submitted_at":"2024-10-11T11:41:02Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages other than English. This underscores the need for careful evaluation of LLMs within each legal system before application. Here, we introduce KBL, a benchmark for assessing the Korean legal language understanding of LLMs, consisting of (1) 7 legal knowledge tasks (510 examples), (2) 4 legal reasoning tasks (288 examples), and (3) the Korean bar exam (4 domains, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08731","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/2410.08731/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":"2410.08731","created_at":"2026-07-05T09:19:16.798060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08731v1","created_at":"2026-07-05T09:19:16.798060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08731","created_at":"2026-07-05T09:19:16.798060+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIZTC55A5AD5","created_at":"2026-07-05T09:19:16.798060+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIZTC55A5AD5LW7F","created_at":"2026-07-05T09:19:16.798060+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIZTC55A","created_at":"2026-07-05T09:19:16.798060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.17111","citing_title":"BLAD: A Historically Contextualized, Multilingual Dataset of Bangladeshi Legal Acts (1799 to 2025)","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV","json":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV.json","graph_json":"https://pith.science/api/pith-number/DIZTC55A5AD5LW7FGWD6OQWFUV/graph.json","events_json":"https://pith.science/api/pith-number/DIZTC55A5AD5LW7FGWD6OQWFUV/events.json","paper":"https://pith.science/paper/DIZTC55A"},"agent_actions":{"view_html":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV","download_json":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV.json","view_paper":"https://pith.science/paper/DIZTC55A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08731&json=true","fetch_graph":"https://pith.science/api/pith-number/DIZTC55A5AD5LW7FGWD6OQWFUV/graph.json","fetch_events":"https://pith.science/api/pith-number/DIZTC55A5AD5LW7FGWD6OQWFUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV/action/storage_attestation","attest_author":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV/action/author_attestation","sign_citation":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV/action/citation_signature","submit_replication":"https://pith.science/pith/DIZTC55A5AD5LW7FGWD6OQWFUV/action/replication_record"}},"created_at":"2026-07-05T09:19:16.798060+00:00","updated_at":"2026-07-05T09:19:16.798060+00:00"}