{"paper":{"title":"The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"People judge AI systems and their designers more deontologically than human actors in the same situations.","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CY","authors_text":"Benjamin Minhao Chen, Xinyu Xie","submitted_at":"2026-04-27T08:12:34Z","abstract_excerpt":"The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act in a given situation. Studies of agent-type value forks challenge this assumption by showing that people do not always judge humans and AI systems identically.This paper extends that challenge by examining two further possibilities: first, that evaluations of AI behavior change when its human origins are made visible; and second, that people judge the humans "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Participants exhibited markedly more deontological, rule-based reasoning when evaluating either the programmed robot or the engineers who programmed it, suggesting that rendering human agency visible activates heightened moral constraints. These findings indicate that people may evaluate humans, AI systems acting in the same situation, and the humans who design them in meaningfully different ways.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That moral judgments elicited by responses to this specific hypothetical runaway mine train scenario are representative of the normative targets that should guide AI behavior in real high-stakes deployment contexts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Moral judgments become more deontological when human design of AI is visible, and designers are judged more strictly than the AI or unaided humans, creating plural and non-converging targets for value alignment.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"People judge AI systems and their designers more deontologically than human actors in the same situations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fd28e2c140f6cabf01635c1671eae64b96a36e495bf51888d7e435a3f1f87666"},"source":{"id":"2604.24155","kind":"arxiv","version":3},"verdict":{"id":"57148808-26af-476e-af4b-55d5adeb1a9b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T07:15:54.517853Z","strongest_claim":"Participants exhibited markedly more deontological, rule-based reasoning when evaluating either the programmed robot or the engineers who programmed it, suggesting that rendering human agency visible activates heightened moral constraints. These findings indicate that people may evaluate humans, AI systems acting in the same situation, and the humans who design them in meaningfully different ways.","one_line_summary":"Moral judgments become more deontological when human design of AI is visible, and designers are judged more strictly than the AI or unaided humans, creating plural and non-converging targets for value alignment.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That moral judgments elicited by responses to this specific hypothetical runaway mine train scenario are representative of the normative targets that should guide AI behavior in real high-stakes deployment contexts.","pith_extraction_headline":"People judge AI systems and their designers more deontologically than human actors in the same situations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24155/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T07:37:46.120051Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:23:37.854729Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9391a6d5244f6482fcaa92034adb7e3773e01e4b5d73add1825013ff1db7c911"},"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"}