{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HCSYV7OHWKYM3PTMHSDN3OAME3","short_pith_number":"pith:HCSYV7OH","schema_version":"1.0","canonical_sha256":"38a58afdc7b2b0cdbe6c3c86ddb80c26f3bfdbc5718f70ab21e5b2b9c15ff636","source":{"kind":"arxiv","id":"2110.07574","version":2},"attestation_state":"computed","paper":{"title":"Can Machines Learn Morality? The Delphi Experiment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Bhagavatula, Jena D. Hwang, Jenny Liang, Jesse Dodge, Jon Borchardt, Keisuke Sakaguchi, Liwei Jiang, Maarten Sap, Maxwell Forbes, Oren Etzioni, Regina Rini, Ronan Le Bras, Saadia Gabriel, Yejin Choi, Yulia Tsvetkov","submitted_at":"2021-10-14T17:38:12Z","abstract_excerpt":"As AI systems become increasingly powerful and pervasive, there are growing concerns about machines' morality or a lack thereof. Yet, teaching morality to machines is a formidable task, as morality remains among the most intensely debated questions in humanity, let alone for AI. Existing AI systems deployed to millions of users, however, are already making decisions loaded with moral implications, which poses a seemingly impossible challenge: teaching machines moral sense, while humanity continues to grapple with it.\n  To explore this challenge, we introduce Delphi, an experimental framework b"},"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":"2110.07574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T17:38:12Z","cross_cats_sorted":[],"title_canon_sha256":"8a6acd7c56645562dfe5ac2c6b24088bfbc800ab2fc54b80e47312f4974c497f","abstract_canon_sha256":"2cae9e90f9007eed1d762ecd422b5397ad7da8c0207a816f25fd687847015ce5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:47.977690Z","signature_b64":"dDyNu2Cj1lFLXtm8ROsFBdDR91K6vTZlc7u7OSYlzn5TUXpy/AfOtfGCybve5Nh3k8nxna9nuJnvmCw+dF/lCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38a58afdc7b2b0cdbe6c3c86ddb80c26f3bfdbc5718f70ab21e5b2b9c15ff636","last_reissued_at":"2026-07-05T04:39:47.977327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:47.977327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Machines Learn Morality? The Delphi Experiment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Bhagavatula, Jena D. Hwang, Jenny Liang, Jesse Dodge, Jon Borchardt, Keisuke Sakaguchi, Liwei Jiang, Maarten Sap, Maxwell Forbes, Oren Etzioni, Regina Rini, Ronan Le Bras, Saadia Gabriel, Yejin Choi, Yulia Tsvetkov","submitted_at":"2021-10-14T17:38:12Z","abstract_excerpt":"As AI systems become increasingly powerful and pervasive, there are growing concerns about machines' morality or a lack thereof. Yet, teaching morality to machines is a formidable task, as morality remains among the most intensely debated questions in humanity, let alone for AI. Existing AI systems deployed to millions of users, however, are already making decisions loaded with moral implications, which poses a seemingly impossible challenge: teaching machines moral sense, while humanity continues to grapple with it.\n  To explore this challenge, we introduce Delphi, an experimental framework b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07574","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/2110.07574/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":"2110.07574","created_at":"2026-07-05T04:39:47.977387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07574v2","created_at":"2026-07-05T04:39:47.977387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07574","created_at":"2026-07-05T04:39:47.977387+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCSYV7OHWKYM","created_at":"2026-07-05T04:39:47.977387+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCSYV7OHWKYM3PTM","created_at":"2026-07-05T04:39:47.977387+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCSYV7OH","created_at":"2026-07-05T04:39:47.977387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13282","citing_title":"ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11635","citing_title":"Are LLMs Bad at Moral Reasoning?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12731","citing_title":"Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2506.00079","citing_title":"Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10162","citing_title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10365","citing_title":"Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08797","citing_title":"Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3","json":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3.json","graph_json":"https://pith.science/api/pith-number/HCSYV7OHWKYM3PTMHSDN3OAME3/graph.json","events_json":"https://pith.science/api/pith-number/HCSYV7OHWKYM3PTMHSDN3OAME3/events.json","paper":"https://pith.science/paper/HCSYV7OH"},"agent_actions":{"view_html":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3","download_json":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3.json","view_paper":"https://pith.science/paper/HCSYV7OH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07574&json=true","fetch_graph":"https://pith.science/api/pith-number/HCSYV7OHWKYM3PTMHSDN3OAME3/graph.json","fetch_events":"https://pith.science/api/pith-number/HCSYV7OHWKYM3PTMHSDN3OAME3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3/action/storage_attestation","attest_author":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3/action/author_attestation","sign_citation":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3/action/citation_signature","submit_replication":"https://pith.science/pith/HCSYV7OHWKYM3PTMHSDN3OAME3/action/replication_record"}},"created_at":"2026-07-05T04:39:47.977387+00:00","updated_at":"2026-07-05T04:39:47.977387+00:00"}