{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5T7UOOAGOWC7IR2OG7IUL2RGSJ","short_pith_number":"pith:5T7UOOAG","schema_version":"1.0","canonical_sha256":"ecff4738067585f4474e37d145ea26925eff24424649c81911d5aeecab093fb2","source":{"kind":"arxiv","id":"2606.11635","version":1},"attestation_state":"computed","paper":{"title":"Are LLMs Bad at Moral Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Menghang Zhu, Seth Lazar","submitted_at":"2026-06-10T03:56:07Z","abstract_excerpt":"For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly. A growing body of research aims to evaluate this capacity -- moral competence -- in today's most capable AI systems, recently reaching broadly pessimistic conclusions. One of the most ambitious such papers collects gold-standard human-authored rubrics for evaluating moral reasoning in 1,000 cases, and benchmarks frontier AI models against those rubrics, with underwhelming results. In t"},"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":"2606.11635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2026-06-10T03:56:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f6a0aa145bd216aa7d516c92f1b116e13d562bdc003f2a0d529ddd0402b12fd","abstract_canon_sha256":"5c52f267af9e868ceecec4a53f214dc68ca438752a6335fe0f0fd18235b04497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:00.119938Z","signature_b64":"vMawxoXRm37phbCuUXymfSt+N29lwXpYjTn49w/LmtgCH6kZ0TGMAFpG8uWh+APLrY6K+4O55WQnbnfC1nEfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecff4738067585f4474e37d145ea26925eff24424649c81911d5aeecab093fb2","last_reissued_at":"2026-06-11T01:10:00.119169Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:00.119169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are LLMs Bad at Moral Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Menghang Zhu, Seth Lazar","submitted_at":"2026-06-10T03:56:07Z","abstract_excerpt":"For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly. A growing body of research aims to evaluate this capacity -- moral competence -- in today's most capable AI systems, recently reaching broadly pessimistic conclusions. One of the most ambitious such papers collects gold-standard human-authored rubrics for evaluating moral reasoning in 1,000 cases, and benchmarks frontier AI models against those rubrics, with underwhelming results. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11635","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/2606.11635/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":"2606.11635","created_at":"2026-06-11T01:10:00.119278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11635v1","created_at":"2026-06-11T01:10:00.119278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11635","created_at":"2026-06-11T01:10:00.119278+00:00"},{"alias_kind":"pith_short_12","alias_value":"5T7UOOAGOWC7","created_at":"2026-06-11T01:10:00.119278+00:00"},{"alias_kind":"pith_short_16","alias_value":"5T7UOOAGOWC7IR2O","created_at":"2026-06-11T01:10:00.119278+00:00"},{"alias_kind":"pith_short_8","alias_value":"5T7UOOAG","created_at":"2026-06-11T01:10:00.119278+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/5T7UOOAGOWC7IR2OG7IUL2RGSJ","json":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ.json","graph_json":"https://pith.science/api/pith-number/5T7UOOAGOWC7IR2OG7IUL2RGSJ/graph.json","events_json":"https://pith.science/api/pith-number/5T7UOOAGOWC7IR2OG7IUL2RGSJ/events.json","paper":"https://pith.science/paper/5T7UOOAG"},"agent_actions":{"view_html":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ","download_json":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ.json","view_paper":"https://pith.science/paper/5T7UOOAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11635&json=true","fetch_graph":"https://pith.science/api/pith-number/5T7UOOAGOWC7IR2OG7IUL2RGSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5T7UOOAGOWC7IR2OG7IUL2RGSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ/action/storage_attestation","attest_author":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ/action/author_attestation","sign_citation":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ/action/citation_signature","submit_replication":"https://pith.science/pith/5T7UOOAGOWC7IR2OG7IUL2RGSJ/action/replication_record"}},"created_at":"2026-06-11T01:10:00.119278+00:00","updated_at":"2026-06-11T01:10:00.119278+00:00"}