{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N6FTKANY22XZC4MMUFFBNMV2DV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"94b10142907024b32406b8bccaa9fcda99df474fd45203ae67e361e0b02b7932","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-03-27T18:12:02Z","title_canon_sha256":"1c35c832d9bb2975f1bb855c98e54a2ab016de3d8cf1215459f7457215bab263"},"schema_version":"1.0","source":{"id":"2404.10636","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10636","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10636v2","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10636","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"N6FTKANY22XZ","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"N6FTKANY22XZC4MM","created_at":"2026-07-05T08:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"N6FTKANY","created_at":"2026-07-05T08:08:58Z"}],"graph_snapshots":[{"event_id":"sha256:d9e701fd404fab1a9f35e7dd94d1a0865baf751de46d414778e76f718a317b5a","target":"graph","created_at":"2026-07-05T08:08:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.10636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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? ","authors_text":"Joe Edelman, Oliver Klingefjord, Ryan Lowe","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-03-27T18:12:02Z","title":"What are human values, and how do we align AI to them?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10636","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5a16f45481db209ded64d24d5c7f9a861bb23fce6850d12e1696d1871596152","target":"record","created_at":"2026-07-05T08:08:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"94b10142907024b32406b8bccaa9fcda99df474fd45203ae67e361e0b02b7932","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-03-27T18:12:02Z","title_canon_sha256":"1c35c832d9bb2975f1bb855c98e54a2ab016de3d8cf1215459f7457215bab263"},"schema_version":"1.0","source":{"id":"2404.10636","kind":"arxiv","version":2}},"canonical_sha256":"6f8b3501b8d6af91718ca14a16b2ba1d715064c78dd6371076d9f56810562613","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f8b3501b8d6af91718ca14a16b2ba1d715064c78dd6371076d9f56810562613","first_computed_at":"2026-07-05T08:08:58.434945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:58.434945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dgpEuj4eKfHoDEXP1YU46wHJhY/fycwJcxc34IbPTOO4ekMIc570+LvI7XojFqSJL3pSAQ3Yp8HnGmPNNjqHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:58.435368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10636","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5a16f45481db209ded64d24d5c7f9a861bb23fce6850d12e1696d1871596152","sha256:d9e701fd404fab1a9f35e7dd94d1a0865baf751de46d414778e76f718a317b5a"],"state_sha256":"14d0e815e526a4fb6a66069e27d7875507d5349672ad1cf984b136f327e4344c"}