{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002392011,0.0003105297,0.0002525696,0.0002928585,0.0007114507,0.0002897505,0.000105193,0.0001088263,0.00003166272],"category_scores_gemma":[0.000242697,0.0002775297,0.00003730876,0.0002685532,0.0000353098,0.0006431989,0.0003723477,0.0006313825,7.456931e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002271484,"about_ca_system_score_gemma":0.00009669246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003725947,"about_ca_topic_score_gemma":0.00008443523,"domain_scores_codex":[0.9980257,0.0002611181,0.0003128615,0.0007458781,0.0003387635,0.0003157048],"domain_scores_gemma":[0.999079,0.0002624768,0.0002996401,0.0001125489,0.0001612025,0.00008510498],"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":[0.000823134,0.0001762363,0.002303603,0.001148146,0.00009376861,0.000003616522,0.02106108,0.9295695,0.004705206,0.0209583,0.000008028214,0.0191494],"study_design_scores_gemma":[0.0005811682,0.0001588697,0.000187558,0.0001351751,0.00006271869,0.00001027533,0.0003280843,0.9678884,0.003863013,0.026415,0.00003652543,0.0003332318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.872213,0.000009794237,0.1187363,0.0001630501,0.00007800408,0.00129108,0.00006713325,0.0003042114,0.007137365],"genre_scores_gemma":[0.9967749,0.00005635871,0.002197462,0.0003307996,0.00007459686,0.0002338617,0.0001372869,0.00002868657,0.0001660716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1245618,"threshold_uncertainty_score":0.9999677,"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."}}