{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MB7R2LNJHJDHJSKF74CYBGV4E6","short_pith_number":"pith:MB7R2LNJ","schema_version":"1.0","canonical_sha256":"607f1d2da93a4674c945ff05809abc27a0205fa7d9009a37c1db0561e747bd2a","source":{"kind":"arxiv","id":"2209.06120","version":1},"attestation_state":"computed","paper":{"title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher R\\'e, Daniel E. Ho, Julian Nyarko, Neel Guha","submitted_at":"2022-09-13T16:11:54Z","abstract_excerpt":"Can foundation models be guided to execute tasks involving legal reasoning? We believe that building a benchmark to answer this question will require sustained collaborative efforts between the computer science and legal communities. To that end, this short paper serves three purposes. First, we describe how IRAC-a framework legal scholars use to distinguish different types of legal reasoning-can guide the construction of a Foundation Model oriented benchmark. Second, we present a seed set of 44 tasks built according to this framework. We discuss initial findings, and highlight directions for "},"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":"2209.06120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-09-13T16:11:54Z","cross_cats_sorted":[],"title_canon_sha256":"a40d07a1434d406c556a3aed84e07d1f11c66c3e8d1b3ca2d7751f31ffa068b7","abstract_canon_sha256":"2dc42def5a3869bd9e85a1559d808d7699c3ff7aca70f52e7ff122445ae8c9db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:20.213423Z","signature_b64":"6KtRviepBZlYY9MwF0oz5XfHiZbN0uvrhfeq5SitwbSkaewrP/j3Fl5q6csBzQTZHSDnDoCD+khvf4/f9Kk5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607f1d2da93a4674c945ff05809abc27a0205fa7d9009a37c1db0561e747bd2a","last_reissued_at":"2026-07-05T04:57:20.212974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:20.212974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher R\\'e, Daniel E. Ho, Julian Nyarko, Neel Guha","submitted_at":"2022-09-13T16:11:54Z","abstract_excerpt":"Can foundation models be guided to execute tasks involving legal reasoning? We believe that building a benchmark to answer this question will require sustained collaborative efforts between the computer science and legal communities. To that end, this short paper serves three purposes. First, we describe how IRAC-a framework legal scholars use to distinguish different types of legal reasoning-can guide the construction of a Foundation Model oriented benchmark. Second, we present a seed set of 44 tasks built according to this framework. We discuss initial findings, and highlight directions for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06120","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/2209.06120/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":"2209.06120","created_at":"2026-07-05T04:57:20.213030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06120v1","created_at":"2026-07-05T04:57:20.213030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06120","created_at":"2026-07-05T04:57:20.213030+00:00"},{"alias_kind":"pith_short_12","alias_value":"MB7R2LNJHJDH","created_at":"2026-07-05T04:57:20.213030+00:00"},{"alias_kind":"pith_short_16","alias_value":"MB7R2LNJHJDHJSKF","created_at":"2026-07-05T04:57:20.213030+00:00"},{"alias_kind":"pith_short_8","alias_value":"MB7R2LNJ","created_at":"2026-07-05T04:57:20.213030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13583","citing_title":"BenGER Platform: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6","json":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6.json","graph_json":"https://pith.science/api/pith-number/MB7R2LNJHJDHJSKF74CYBGV4E6/graph.json","events_json":"https://pith.science/api/pith-number/MB7R2LNJHJDHJSKF74CYBGV4E6/events.json","paper":"https://pith.science/paper/MB7R2LNJ"},"agent_actions":{"view_html":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6","download_json":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6.json","view_paper":"https://pith.science/paper/MB7R2LNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06120&json=true","fetch_graph":"https://pith.science/api/pith-number/MB7R2LNJHJDHJSKF74CYBGV4E6/graph.json","fetch_events":"https://pith.science/api/pith-number/MB7R2LNJHJDHJSKF74CYBGV4E6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6/action/storage_attestation","attest_author":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6/action/author_attestation","sign_citation":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6/action/citation_signature","submit_replication":"https://pith.science/pith/MB7R2LNJHJDHJSKF74CYBGV4E6/action/replication_record"}},"created_at":"2026-07-05T04:57:20.213030+00:00","updated_at":"2026-07-05T04:57:20.213030+00:00"}