{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B6UYJJQUV6GU5E36SV7CWWLBRZ","short_pith_number":"pith:B6UYJJQU","schema_version":"1.0","canonical_sha256":"0fa984a614af8d4e937e957e2b59618e70101448599e8abce72c3b13d4ff359e","source":{"kind":"arxiv","id":"2506.04636","version":2},"attestation_state":"computed","paper":{"title":"CHANCERY: Evaluating Corporate Governance Reasoning Capabilities in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Arda Kaz, Lucas Irwin, Peiyao Sheng, Pramod Viswanath, Sewoong Oh","submitted_at":"2025-06-05T05:13:32Z","abstract_excerpt":"Law has long been a domain that has been popular in natural language processing (NLP) applications. Reasoning (ratiocination and the ability to make connections to precedent) is a core part of the practice of the law in the real world. Nevertheless, while multiple legal datasets exist, none have thus far focused specifically on reasoning tasks. We focus on a specific aspect of the legal landscape by introducing a corporate governance reasoning benchmark (CHANCERY) to test a model's ability to reason about whether executive/board/shareholder's proposed actions are consistent with corporate gove"},"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":"2506.04636","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T05:13:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c794de95c9ffd5157552adadc28d589bf7e87f2ee0c6d54c652673f09402ce46","abstract_canon_sha256":"0b3213ed473fc527f48dde0cf0e9088d81f062fd95ea2c607fb9dae8763d7ccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:12.831463Z","signature_b64":"VU5AICdL9zal8bt6Hdziy2lUy+ljzUJeKHS95Tr07Q17MLRlfhtv8tGRVBtRQ+OFTkYhT53+dkVkWAczvgX6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa984a614af8d4e937e957e2b59618e70101448599e8abce72c3b13d4ff359e","last_reissued_at":"2026-07-05T11:20:12.830749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:12.830749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHANCERY: Evaluating Corporate Governance Reasoning Capabilities in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Arda Kaz, Lucas Irwin, Peiyao Sheng, Pramod Viswanath, Sewoong Oh","submitted_at":"2025-06-05T05:13:32Z","abstract_excerpt":"Law has long been a domain that has been popular in natural language processing (NLP) applications. Reasoning (ratiocination and the ability to make connections to precedent) is a core part of the practice of the law in the real world. Nevertheless, while multiple legal datasets exist, none have thus far focused specifically on reasoning tasks. We focus on a specific aspect of the legal landscape by introducing a corporate governance reasoning benchmark (CHANCERY) to test a model's ability to reason about whether executive/board/shareholder's proposed actions are consistent with corporate gove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04636","kind":"arxiv","version":2},"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/2506.04636/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":"2506.04636","created_at":"2026-07-05T11:20:12.830840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04636v2","created_at":"2026-07-05T11:20:12.830840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04636","created_at":"2026-07-05T11:20:12.830840+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6UYJJQUV6GU","created_at":"2026-07-05T11:20:12.830840+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6UYJJQUV6GU5E36","created_at":"2026-07-05T11:20:12.830840+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6UYJJQU","created_at":"2026-07-05T11:20:12.830840+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/B6UYJJQUV6GU5E36SV7CWWLBRZ","json":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ.json","graph_json":"https://pith.science/api/pith-number/B6UYJJQUV6GU5E36SV7CWWLBRZ/graph.json","events_json":"https://pith.science/api/pith-number/B6UYJJQUV6GU5E36SV7CWWLBRZ/events.json","paper":"https://pith.science/paper/B6UYJJQU"},"agent_actions":{"view_html":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ","download_json":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ.json","view_paper":"https://pith.science/paper/B6UYJJQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04636&json=true","fetch_graph":"https://pith.science/api/pith-number/B6UYJJQUV6GU5E36SV7CWWLBRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/B6UYJJQUV6GU5E36SV7CWWLBRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ/action/storage_attestation","attest_author":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ/action/author_attestation","sign_citation":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ/action/citation_signature","submit_replication":"https://pith.science/pith/B6UYJJQUV6GU5E36SV7CWWLBRZ/action/replication_record"}},"created_at":"2026-07-05T11:20:12.830840+00:00","updated_at":"2026-07-05T11:20:12.830840+00:00"}