{"id":"W4396883611","doi":"10.31234/osf.io/uc6d4","title":"Prompting sometimes invokes expert-like downward shifts in multimodal models’ conceptual hierarchies","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Psychology; Cognitive psychology; Epistemology; Cognitive science; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001668433,0.0004834001,0.0003178322,0.0002268121,0.0002616048,0.000768888,0.0007104743,0.001231625,0.005764754],"category_scores_gemma":[0.01609604,0.0003242058,0.0002505238,0.0001094899,0.0005667136,0.001650363,0.001769511,0.001222331,0.0008437772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004371406,"about_ca_system_score_gemma":0.000296948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006427753,"about_ca_topic_score_gemma":0.0009791488,"domain_scores_codex":[0.9984733,0.000541773,0.0001027621,0.0003906033,0.0003680485,0.0001234986],"domain_scores_gemma":[0.9914047,0.005025331,0.0007756791,0.00187303,0.0003459962,0.0005752907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008471675,0.0004482005,0.02780976,0.0004379415,0.00003683319,0.001286323,0.008539209,0.001929818,0.8984441,0.003384297,0.002074667,0.05476165],"study_design_scores_gemma":[0.0003646295,0.005960173,0.30496,0.0001679387,0.0001667352,0.006544864,0.00890102,0.0619009,0.5481545,0.02609314,0.03648376,0.0003022888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754111,0.00006540398,0.01757871,0.0001799566,0.00002247053,0.00006255286,0.00006698565,0.001216672,0.005396063],"genre_scores_gemma":[0.9874516,0.00003303135,0.01076315,0.000162908,0.000006960318,0.00006835703,0.0001441585,0.000100185,0.001269655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005764754,"threshold_uncertainty_score":0.01928502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04430763271231802,"score_gpt":0.2735097836492447,"score_spread":0.2292021509369266,"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."}}