{"id":"W4294384670","doi":"10.31234/osf.io/k4cas","title":"Value Cores for Inner and Outer Alignment: Simulating Personality Formation via Iterated Policy Selection and Preference Learning with Self-World Modeling Active Inference Agents","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Embodied and Extended Cognition","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Inference; Counterfactual thinking; Machine learning; Cognitive science; Human–computer interaction; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008026218,0.0003380812,0.0005916368,0.0003623126,0.0005076305,0.001066129,0.001062423,0.001062345,0.003444748],"category_scores_gemma":[0.004335314,0.0003649136,0.0006095858,0.0002852739,0.001127039,0.00114272,0.001018625,0.00101322,0.0002190516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001072014,"about_ca_system_score_gemma":0.0009181224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01031393,"about_ca_topic_score_gemma":0.00882931,"domain_scores_codex":[0.9997912,0.0001045254,0.000006159419,0.00002749774,0.00002376882,0.00004692589],"domain_scores_gemma":[0.9983786,0.001046971,0.0001481034,0.0001173404,0.00009116906,0.0002177779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001064127,0.00007408687,0.002409958,0.00002126435,0.00003376736,0.00009758933,0.0002029151,0.9618657,0.0005474738,0.02941633,0.0004009295,0.004823581],"study_design_scores_gemma":[0.00000962743,0.000007379396,0.00008730688,0.000001571374,0.000002140464,0.000002581873,0.0000117772,0.9950205,0.00005331967,0.00474263,0.00005854735,0.000002522906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7846407,0.0001526464,0.2038629,0.0009659324,0.00006938376,0.00005692611,0.000130662,0.0002440022,0.009876796],"genre_scores_gemma":[0.9848477,0.00003231019,0.01385571,0.00006142974,0.000008225433,0.00003715654,0.00003384717,0.0000206592,0.001102833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01031393,"threshold_uncertainty_score":0.02050781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08839334115988134,"score_gpt":0.3252403399139924,"score_spread":0.236846998754111,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}