{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MZDA4Z46CJSEYQGS62TTZWK3J2","short_pith_number":"pith:MZDA4Z46","schema_version":"1.0","canonical_sha256":"66460e679e12644c40d2f6a73cd95b4eb9099164dd16bfb50daf1559ca2ff91e","source":{"kind":"arxiv","id":"2507.17216","version":1},"attestation_state":"computed","paper":{"title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Debora Nozza, Dirk Hovy, Giuseppe Russo, Paul R\\\"ottger","submitted_at":"2025-07-23T05:26:17Z","abstract_excerpt":"People increasingly rely on Large Language Models (LLMs) for moral advice, which may influence humans' decisions. Yet, little is known about how closely LLMs align with human moral judgments. To address this, we introduce the Moral Dilemma Dataset, a benchmark of 1,618 real-world moral dilemmas paired with a distribution of human moral judgments consisting of a binary evaluation and a free-text rationale. We treat this problem as a pluralistic distributional alignment task, comparing the distributions of LLM and human judgments across dilemmas. We find that models reproduce human judgments onl"},"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":"2507.17216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T05:26:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3352a1136187562006c3839d6960f311b3818331e3624645ff3bf3011aa9b432","abstract_canon_sha256":"21d61b47efb349134d9c196a9a2f80fbcbaafeca330d9eefaa3d9748a8c9026f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:03.624129Z","signature_b64":"J3ilQhO6G6tEyFJtrZ7zs7UBWwEJ9Xo1ASSmJzNllgxCceGoJTwIXPtvqrNh2faCDuJ1gmiZ6o1CivLZwm3BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66460e679e12644c40d2f6a73cd95b4eb9099164dd16bfb50daf1559ca2ff91e","last_reissued_at":"2026-07-05T11:42:03.623618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:03.623618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Debora Nozza, Dirk Hovy, Giuseppe Russo, Paul R\\\"ottger","submitted_at":"2025-07-23T05:26:17Z","abstract_excerpt":"People increasingly rely on Large Language Models (LLMs) for moral advice, which may influence humans' decisions. Yet, little is known about how closely LLMs align with human moral judgments. To address this, we introduce the Moral Dilemma Dataset, a benchmark of 1,618 real-world moral dilemmas paired with a distribution of human moral judgments consisting of a binary evaluation and a free-text rationale. We treat this problem as a pluralistic distributional alignment task, comparing the distributions of LLM and human judgments across dilemmas. We find that models reproduce human judgments onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17216","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/2507.17216/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":"2507.17216","created_at":"2026-07-05T11:42:03.623685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17216v1","created_at":"2026-07-05T11:42:03.623685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17216","created_at":"2026-07-05T11:42:03.623685+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZDA4Z46CJSE","created_at":"2026-07-05T11:42:03.623685+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZDA4Z46CJSEYQGS","created_at":"2026-07-05T11:42:03.623685+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZDA4Z46","created_at":"2026-07-05T11:42:03.623685+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/MZDA4Z46CJSEYQGS62TTZWK3J2","json":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2.json","graph_json":"https://pith.science/api/pith-number/MZDA4Z46CJSEYQGS62TTZWK3J2/graph.json","events_json":"https://pith.science/api/pith-number/MZDA4Z46CJSEYQGS62TTZWK3J2/events.json","paper":"https://pith.science/paper/MZDA4Z46"},"agent_actions":{"view_html":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2","download_json":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2.json","view_paper":"https://pith.science/paper/MZDA4Z46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17216&json=true","fetch_graph":"https://pith.science/api/pith-number/MZDA4Z46CJSEYQGS62TTZWK3J2/graph.json","fetch_events":"https://pith.science/api/pith-number/MZDA4Z46CJSEYQGS62TTZWK3J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2/action/storage_attestation","attest_author":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2/action/author_attestation","sign_citation":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2/action/citation_signature","submit_replication":"https://pith.science/pith/MZDA4Z46CJSEYQGS62TTZWK3J2/action/replication_record"}},"created_at":"2026-07-05T11:42:03.623685+00:00","updated_at":"2026-07-05T11:42:03.623685+00:00"}