{"id":"W4412456738","doi":"10.1111/mila.12537","title":"Deference, development, and large language models: Issues at the edge of sentience","year":2025,"lang":"en","type":"article","venue":"Mind & Language","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Canadian Institute for Advanced Research","keywords":"Sentience; Deference; Psychology; Epistemology; Cognitive science; Philosophy; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002685917,0.0001284539,0.0001681906,0.00007667274,0.0001511575,0.000020236,0.000183413,0.00006230594,0.001102507],"category_scores_gemma":[0.00002721083,0.00008954345,0.00003487654,0.0001749618,0.00007978899,0.00003504022,0.0002001444,0.0001297413,0.0001171577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002139986,"about_ca_system_score_gemma":0.00003896972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008640974,"about_ca_topic_score_gemma":0.0002312932,"domain_scores_codex":[0.9990851,0.00006114274,0.0002029659,0.0002791944,0.0001183363,0.0002532443],"domain_scores_gemma":[0.999566,0.0000625201,0.00006633688,0.0002491644,0.00002120596,0.00003476792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001698917,0.0003796887,0.05315339,0.0001421685,0.0003184014,0.0001426306,0.5499915,0.00000447029,0.006738265,0.02917763,0.01723885,0.3425431],"study_design_scores_gemma":[0.001916367,0.00007049483,0.3685899,0.0003306828,0.00008149921,0.00003413589,0.09550054,0.0001213947,0.0269944,0.0002382213,0.5055068,0.0006155802],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9216471,0.009016523,0.0001812058,0.0002000106,0.0001356232,0.0001199531,0.00001653772,0.00002218271,0.0686608],"genre_scores_gemma":[0.9255855,0.00001294008,0.0005510717,0.000246114,0.00002852338,0.00001276382,0.00002198971,0.000008202545,0.07353288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4882679,"threshold_uncertainty_score":0.9998106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01626726467484672,"score_gpt":0.3081176076615687,"score_spread":0.291850342986722,"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."}}