{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J76LGJJHH4LQULA36C4QJWFLAD","short_pith_number":"pith:J76LGJJH","schema_version":"1.0","canonical_sha256":"4ffcb325273f170a2c1bf0b904d8ab00eae7e1591c2d0c4522c98bc5b9783ab6","source":{"kind":"arxiv","id":"2412.17259","version":1},"attestation_state":"computed","paper":{"title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guozhi Yuan, Haitao Li, Jingli Yang, Junjie Chen, Kai Lin, Minlie Huang, Qingyao Ai, Wei Jia, Wuyue Wang, Yiqun Liu, Yiran Hu, Youfeng Liu, Yueyue Wu","submitted_at":"2024-12-23T04:02:46Z","abstract_excerpt":"With the increasing intelligence and autonomy of LLM agents, their potential applications in the legal domain are becoming increasingly apparent. However, existing general-domain benchmarks cannot fully capture the complexity and subtle nuances of real-world judicial cognition and decision-making. Therefore, we propose LegalAgentBench, a comprehensive benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain. LegalAgentBench includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge. We designed a scalable task con"},"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":"2412.17259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T04:02:46Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"393917ec728303f4c556f71b181538dc54697593431c7303f3a1d29d0ff59312","abstract_canon_sha256":"837cbf6833d0a08a651d06eef2efd5cb1d36d6f4bfe132ef3e2d84a130d6f0df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:19.706796Z","signature_b64":"WtD0nXZN8DFTW0/DglCpVfNBCl6eGXH/i1DtjY1Ol6FdwtuHYVzvVmFaNw8pgEA232OUURQw+gciOb8sfmA+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ffcb325273f170a2c1bf0b904d8ab00eae7e1591c2d0c4522c98bc5b9783ab6","last_reissued_at":"2026-07-05T09:53:19.706374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:19.706374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guozhi Yuan, Haitao Li, Jingli Yang, Junjie Chen, Kai Lin, Minlie Huang, Qingyao Ai, Wei Jia, Wuyue Wang, Yiqun Liu, Yiran Hu, Youfeng Liu, Yueyue Wu","submitted_at":"2024-12-23T04:02:46Z","abstract_excerpt":"With the increasing intelligence and autonomy of LLM agents, their potential applications in the legal domain are becoming increasingly apparent. However, existing general-domain benchmarks cannot fully capture the complexity and subtle nuances of real-world judicial cognition and decision-making. Therefore, we propose LegalAgentBench, a comprehensive benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain. LegalAgentBench includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge. We designed a scalable task con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17259","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/2412.17259/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":"2412.17259","created_at":"2026-07-05T09:53:19.706430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17259v1","created_at":"2026-07-05T09:53:19.706430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17259","created_at":"2026-07-05T09:53:19.706430+00:00"},{"alias_kind":"pith_short_12","alias_value":"J76LGJJHH4LQ","created_at":"2026-07-05T09:53:19.706430+00:00"},{"alias_kind":"pith_short_16","alias_value":"J76LGJJHH4LQULA3","created_at":"2026-07-05T09:53:19.706430+00:00"},{"alias_kind":"pith_short_8","alias_value":"J76LGJJH","created_at":"2026-07-05T09:53:19.706430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.04023","citing_title":"Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09747","citing_title":"ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD","json":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD.json","graph_json":"https://pith.science/api/pith-number/J76LGJJHH4LQULA36C4QJWFLAD/graph.json","events_json":"https://pith.science/api/pith-number/J76LGJJHH4LQULA36C4QJWFLAD/events.json","paper":"https://pith.science/paper/J76LGJJH"},"agent_actions":{"view_html":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD","download_json":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD.json","view_paper":"https://pith.science/paper/J76LGJJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17259&json=true","fetch_graph":"https://pith.science/api/pith-number/J76LGJJHH4LQULA36C4QJWFLAD/graph.json","fetch_events":"https://pith.science/api/pith-number/J76LGJJHH4LQULA36C4QJWFLAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD/action/storage_attestation","attest_author":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD/action/author_attestation","sign_citation":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD/action/citation_signature","submit_replication":"https://pith.science/pith/J76LGJJHH4LQULA36C4QJWFLAD/action/replication_record"}},"created_at":"2026-07-05T09:53:19.706430+00:00","updated_at":"2026-07-05T09:53:19.706430+00:00"}