{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N6FTKANY22XZC4MMUFFBNMV2DV","short_pith_number":"pith:N6FTKANY","schema_version":"1.0","canonical_sha256":"6f8b3501b8d6af91718ca14a16b2ba1d715064c78dd6371076d9f56810562613","source":{"kind":"arxiv","id":"2404.10636","version":2},"attestation_state":"computed","paper":{"title":"What are human values, and how do we align AI to them?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.CY","authors_text":"Joe Edelman, Oliver Klingefjord, Ryan Lowe","submitted_at":"2024-03-27T18:12:02Z","abstract_excerpt":"There is an emerging consensus that we need to align AI systems with human values (Gabriel, 2020; Ji et al., 2024), but it remains unclear how to apply this to language models in practice. We split the problem of \"aligning to human values\" into three parts: first, eliciting values from people; second, reconciling those values into an alignment target for training ML models; and third, actually training the model. In this paper, we focus on the first two parts, and ask the question: what are \"good\" ways to synthesize diverse human inputs about values into a target for aligning language models? "},"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":"2404.10636","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-03-27T18:12:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"title_canon_sha256":"1c35c832d9bb2975f1bb855c98e54a2ab016de3d8cf1215459f7457215bab263","abstract_canon_sha256":"94b10142907024b32406b8bccaa9fcda99df474fd45203ae67e361e0b02b7932"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:58.435368Z","signature_b64":"dgpEuj4eKfHoDEXP1YU46wHJhY/fycwJcxc34IbPTOO4ekMIc570+LvI7XojFqSJL3pSAQ3Yp8HnGmPNNjqHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f8b3501b8d6af91718ca14a16b2ba1d715064c78dd6371076d9f56810562613","last_reissued_at":"2026-07-05T08:08:58.434945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:58.434945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What are human values, and how do we align AI to them?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.CY","authors_text":"Joe Edelman, Oliver Klingefjord, Ryan Lowe","submitted_at":"2024-03-27T18:12:02Z","abstract_excerpt":"There is an emerging consensus that we need to align AI systems with human values (Gabriel, 2020; Ji et al., 2024), but it remains unclear how to apply this to language models in practice. We split the problem of \"aligning to human values\" into three parts: first, eliciting values from people; second, reconciling those values into an alignment target for training ML models; and third, actually training the model. In this paper, we focus on the first two parts, and ask the question: what are \"good\" ways to synthesize diverse human inputs about values into a target for aligning language models? "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10636","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/2404.10636/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":"2404.10636","created_at":"2026-07-05T08:08:58.434997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10636v2","created_at":"2026-07-05T08:08:58.434997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10636","created_at":"2026-07-05T08:08:58.434997+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6FTKANY22XZ","created_at":"2026-07-05T08:08:58.434997+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6FTKANY22XZC4MM","created_at":"2026-07-05T08:08:58.434997+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6FTKANY","created_at":"2026-07-05T08:08:58.434997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20512","citing_title":"Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17815","citing_title":"Navigating the Conceptual Multiverse","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21864","citing_title":"FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism","ref_index":107,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV","json":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV.json","graph_json":"https://pith.science/api/pith-number/N6FTKANY22XZC4MMUFFBNMV2DV/graph.json","events_json":"https://pith.science/api/pith-number/N6FTKANY22XZC4MMUFFBNMV2DV/events.json","paper":"https://pith.science/paper/N6FTKANY"},"agent_actions":{"view_html":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV","download_json":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV.json","view_paper":"https://pith.science/paper/N6FTKANY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10636&json=true","fetch_graph":"https://pith.science/api/pith-number/N6FTKANY22XZC4MMUFFBNMV2DV/graph.json","fetch_events":"https://pith.science/api/pith-number/N6FTKANY22XZC4MMUFFBNMV2DV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV/action/storage_attestation","attest_author":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV/action/author_attestation","sign_citation":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV/action/citation_signature","submit_replication":"https://pith.science/pith/N6FTKANY22XZC4MMUFFBNMV2DV/action/replication_record"}},"created_at":"2026-07-05T08:08:58.434997+00:00","updated_at":"2026-07-05T08:08:58.434997+00:00"}