{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KGNB4VYGCDSR3N4F3ZJR5IMU2W","short_pith_number":"pith:KGNB4VYG","schema_version":"1.0","canonical_sha256":"519a1e570610e51db785de531ea194d5a1491d7415036ab84f234b3575bb8039","source":{"kind":"arxiv","id":"2404.10975","version":1},"attestation_state":"computed","paper":{"title":"Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayesha Khawaja, Jan-Philipp Fr\\\"anken, Kanishk Gandhi, Noah D. Goodman, Tobias Gerstenberg, Tori Qiu","submitted_at":"2024-04-17T01:13:04Z","abstract_excerpt":"As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral reasoning. To test whether they do, we need to develop systematic evaluations. We provide a framework that uses a language model to translate causal graphs that capture key aspects of moral dilemmas into prompt templates. With this framework, we procedurally generated a large and diverse set of moral dilemmas -- the OffTheRails benchmark -- consisting of 50 scenarios and 400 unique test items. We collected moral perm"},"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":"2404.10975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-17T01:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"a5fdcb07190f4436252abd26bc469f106091aaab576af7462c8b74b7d6a7f3fd","abstract_canon_sha256":"78d5c2d75f171f6a312b10cb8628968bb6bfe2393a666e0eae86678293b7386c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:01.604484Z","signature_b64":"7O279MM0U3SpCSnySbhHv3yK0SsmYFcQZm4i6tcHXmwqbRCAFUWV0AJIJ1B+TMKCeDxuQhXQ1QwF8KX5BfCkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"519a1e570610e51db785de531ea194d5a1491d7415036ab84f234b3575bb8039","last_reissued_at":"2026-07-05T08:09:01.604008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:01.604008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayesha Khawaja, Jan-Philipp Fr\\\"anken, Kanishk Gandhi, Noah D. Goodman, Tobias Gerstenberg, Tori Qiu","submitted_at":"2024-04-17T01:13:04Z","abstract_excerpt":"As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral reasoning. To test whether they do, we need to develop systematic evaluations. We provide a framework that uses a language model to translate causal graphs that capture key aspects of moral dilemmas into prompt templates. With this framework, we procedurally generated a large and diverse set of moral dilemmas -- the OffTheRails benchmark -- consisting of 50 scenarios and 400 unique test items. We collected moral perm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10975","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/2404.10975/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":"2404.10975","created_at":"2026-07-05T08:09:01.604062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10975v1","created_at":"2026-07-05T08:09:01.604062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10975","created_at":"2026-07-05T08:09:01.604062+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGNB4VYGCDSR","created_at":"2026-07-05T08:09:01.604062+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGNB4VYGCDSR3N4F","created_at":"2026-07-05T08:09:01.604062+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGNB4VYG","created_at":"2026-07-05T08:09:01.604062+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/KGNB4VYGCDSR3N4F3ZJR5IMU2W","json":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W.json","graph_json":"https://pith.science/api/pith-number/KGNB4VYGCDSR3N4F3ZJR5IMU2W/graph.json","events_json":"https://pith.science/api/pith-number/KGNB4VYGCDSR3N4F3ZJR5IMU2W/events.json","paper":"https://pith.science/paper/KGNB4VYG"},"agent_actions":{"view_html":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W","download_json":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W.json","view_paper":"https://pith.science/paper/KGNB4VYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10975&json=true","fetch_graph":"https://pith.science/api/pith-number/KGNB4VYGCDSR3N4F3ZJR5IMU2W/graph.json","fetch_events":"https://pith.science/api/pith-number/KGNB4VYGCDSR3N4F3ZJR5IMU2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W/action/storage_attestation","attest_author":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W/action/author_attestation","sign_citation":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W/action/citation_signature","submit_replication":"https://pith.science/pith/KGNB4VYGCDSR3N4F3ZJR5IMU2W/action/replication_record"}},"created_at":"2026-07-05T08:09:01.604062+00:00","updated_at":"2026-07-05T08:09:01.604062+00:00"}