{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TAW4RDZABLJBBY4KLQBUJCSKVO","short_pith_number":"pith:TAW4RDZA","schema_version":"1.0","canonical_sha256":"982dc88f200ad210e38a5c03448a4aab85b6db3b91ae4979013e12c1c75ef14d","source":{"kind":"arxiv","id":"2008.02275","version":6},"attestation_state":"computed","paper":{"title":"Aligning AI With Shared Human Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CY","authors_text":"Andrew Critch, Collin Burns, Dan Hendrycks, Dawn Song, Jacob Steinhardt, Jerry Li, Steven Basart","submitted_at":"2020-08-05T17:59:16Z","abstract_excerpt":"We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to steer chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete ability to"},"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":"2008.02275","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2020-08-05T17:59:16Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"94989c8f95bb553dfce87bace4d348a496a80b36ac09a26fcaa755065a2c2e1f","abstract_canon_sha256":"5cbda22775e7f736bec170ffeea33ce0b7886f1510a37f666ee4258ca2804de6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T14:33:20.420476Z","signature_b64":"/Y/UJ6+SEW3aVdUV2K5QsNoS8EKb3CvhbOLwGWQ/7vdDC8Olj+n3esjr82ZAwDxRSN3NoL6G1Bpuei9XhhfoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"982dc88f200ad210e38a5c03448a4aab85b6db3b91ae4979013e12c1c75ef14d","last_reissued_at":"2026-05-21T14:33:20.418372Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T14:33:20.418372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning AI With Shared Human Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CY","authors_text":"Andrew Critch, Collin Burns, Dan Hendrycks, Dawn Song, Jacob Steinhardt, Jerry Li, Steven Basart","submitted_at":"2020-08-05T17:59:16Z","abstract_excerpt":"We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to steer chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete ability to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02275","kind":"arxiv","version":6},"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/2008.02275/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":"2008.02275","created_at":"2026-05-21T14:33:20.418479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02275v6","created_at":"2026-05-21T14:33:20.418479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02275","created_at":"2026-05-21T14:33:20.418479+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAW4RDZABLJB","created_at":"2026-05-21T14:33:20.418479+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAW4RDZABLJBBY4K","created_at":"2026-05-21T14:33:20.418479+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAW4RDZA","created_at":"2026-05-21T14:33:20.418479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2605.23420","citing_title":"Naturalistic measure of social norms alignment","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2502.19559","citing_title":"Stay Focused: Problem Drift in Multi-Agent Debate","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04062","citing_title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22739","citing_title":"Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21095","citing_title":"Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16301","citing_title":"MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18423","citing_title":"REBAR: Reference Ethical Benchmark for Autonomy Readiness","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18660","citing_title":"Evaluating Multi-turn Human-AI Interaction","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":226,"is_internal_anchor":true},{"citing_arxiv_id":"2402.05070","citing_title":"A Roadmap to Pluralistic Alignment","ref_index":257,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12809","citing_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","ref_index":226,"is_internal_anchor":true},{"citing_arxiv_id":"2406.04093","citing_title":"Scaling and evaluating sparse autoencoders","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08496","citing_title":"Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2112.04359","citing_title":"Ethical and social risks of harm from Language Models","ref_index":110,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00957","citing_title":"\"I Don't Know\" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00874","citing_title":"Latent Space Probing for Adult Content Detection in Video Generative Models","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":223,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19016","citing_title":"AlignCultura: Towards Culturally Aligned Large Language Models?","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11216","citing_title":"Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04062","citing_title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05339","citing_title":"Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":217,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19125","citing_title":"Do Emotions Influence Moral Judgment in Large Language Models?","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20805","citing_title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO","json":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO.json","graph_json":"https://pith.science/api/pith-number/TAW4RDZABLJBBY4KLQBUJCSKVO/graph.json","events_json":"https://pith.science/api/pith-number/TAW4RDZABLJBBY4KLQBUJCSKVO/events.json","paper":"https://pith.science/paper/TAW4RDZA"},"agent_actions":{"view_html":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO","download_json":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO.json","view_paper":"https://pith.science/paper/TAW4RDZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02275&json=true","fetch_graph":"https://pith.science/api/pith-number/TAW4RDZABLJBBY4KLQBUJCSKVO/graph.json","fetch_events":"https://pith.science/api/pith-number/TAW4RDZABLJBBY4KLQBUJCSKVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO/action/storage_attestation","attest_author":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO/action/author_attestation","sign_citation":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO/action/citation_signature","submit_replication":"https://pith.science/pith/TAW4RDZABLJBBY4KLQBUJCSKVO/action/replication_record"}},"created_at":"2026-05-21T14:33:20.418479+00:00","updated_at":"2026-05-21T14:33:20.418479+00:00"}