{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UCOPT4MN63XVL4UBBQJUKZQA2O","short_pith_number":"pith:UCOPT4MN","schema_version":"1.0","canonical_sha256":"a09cf9f18df6ef55f2810c13456600d388dc105f153e415a01c61626e61250e1","source":{"kind":"arxiv","id":"2411.10534","version":1},"attestation_state":"computed","paper":{"title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.HC","authors_text":"Amy X. Zhang, Andrew Konya, Aviv Ovadya, Colin Irwin, Kevin Feng, Lisa Schirch, Quan Ze Chen","submitted_at":"2024-11-15T19:10:39Z","abstract_excerpt":"We introduce a method to measure the alignment between public will and language model (LM) behavior that can be applied to fine-tuning, online oversight, and pre-release safety checks. Our `chain of alignment' (CoA) approach produces a rule based reward (RBR) by creating model behavior $\\textit{rules}$ aligned to normative $\\textit{objectives}$ aligned to $\\textit{public will}$. This factoring enables a nonexpert public to directly specify their will through the normative objectives, while expert intelligence is used to figure out rules entailing model behavior that best achieves those objecti"},"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":"2411.10534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-11-15T19:10:39Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"63b565756aa02ce6cb388aa681ae2dd5ee1b8834991b6f9c9c8d1d4f231c2dd3","abstract_canon_sha256":"b90185f2c255a61fe85b4aaf6ef542ab360326db98111d144dd1fc1d7a7351bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:18.221159Z","signature_b64":"tiBNpBZ9fkaQj1hRO4xgzCKiwcRniRAtvpztfC94S2Mr94bdDAUoCz/OPMTKPd9+XofSgCDUHdbIexf19XbtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a09cf9f18df6ef55f2810c13456600d388dc105f153e415a01c61626e61250e1","last_reissued_at":"2026-07-05T09:36:18.220731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:18.220731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.HC","authors_text":"Amy X. Zhang, Andrew Konya, Aviv Ovadya, Colin Irwin, Kevin Feng, Lisa Schirch, Quan Ze Chen","submitted_at":"2024-11-15T19:10:39Z","abstract_excerpt":"We introduce a method to measure the alignment between public will and language model (LM) behavior that can be applied to fine-tuning, online oversight, and pre-release safety checks. Our `chain of alignment' (CoA) approach produces a rule based reward (RBR) by creating model behavior $\\textit{rules}$ aligned to normative $\\textit{objectives}$ aligned to $\\textit{public will}$. This factoring enables a nonexpert public to directly specify their will through the normative objectives, while expert intelligence is used to figure out rules entailing model behavior that best achieves those objecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10534","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/2411.10534/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":"2411.10534","created_at":"2026-07-05T09:36:18.220783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10534v1","created_at":"2026-07-05T09:36:18.220783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10534","created_at":"2026-07-05T09:36:18.220783+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCOPT4MN63XV","created_at":"2026-07-05T09:36:18.220783+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCOPT4MN63XVL4UB","created_at":"2026-07-05T09:36:18.220783+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCOPT4MN","created_at":"2026-07-05T09:36:18.220783+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/UCOPT4MN63XVL4UBBQJUKZQA2O","json":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O.json","graph_json":"https://pith.science/api/pith-number/UCOPT4MN63XVL4UBBQJUKZQA2O/graph.json","events_json":"https://pith.science/api/pith-number/UCOPT4MN63XVL4UBBQJUKZQA2O/events.json","paper":"https://pith.science/paper/UCOPT4MN"},"agent_actions":{"view_html":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O","download_json":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O.json","view_paper":"https://pith.science/paper/UCOPT4MN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10534&json=true","fetch_graph":"https://pith.science/api/pith-number/UCOPT4MN63XVL4UBBQJUKZQA2O/graph.json","fetch_events":"https://pith.science/api/pith-number/UCOPT4MN63XVL4UBBQJUKZQA2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O/action/storage_attestation","attest_author":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O/action/author_attestation","sign_citation":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O/action/citation_signature","submit_replication":"https://pith.science/pith/UCOPT4MN63XVL4UBBQJUKZQA2O/action/replication_record"}},"created_at":"2026-07-05T09:36:18.220783+00:00","updated_at":"2026-07-05T09:36:18.220783+00:00"}