{"id":"W4416736678","doi":"10.2139/ssrn.5788402","title":"Learning to Prompt: Human Adaptation in Production with Generative AI","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Generative grammar; Complementarity (molecular biology); Adaptation (eye); Process (computing); Feature (linguistics)","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":[0.00533365,0.0003899266,0.0002321158,0.0005688537,0.00104753,0.00384554,0.0009636538,0.00175789,0.009322666],"category_scores_gemma":[0.03692063,0.0003495475,0.0003204467,0.0005662614,0.006061221,0.004024173,0.002897915,0.001724127,0.0009939418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074927,"about_ca_system_score_gemma":0.001028577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001072238,"about_ca_topic_score_gemma":0.0007368386,"domain_scores_codex":[0.9944983,0.004196688,0.00008463184,0.000516914,0.00046236,0.0002411387],"domain_scores_gemma":[0.9758354,0.0178376,0.0009871484,0.003771648,0.0008942559,0.0006739192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0008915429,0.0009175821,0.03722825,0.0004951023,0.0001220667,0.001940703,0.08403848,0.04689365,0.04077365,0.4963247,0.007176091,0.2831982],"study_design_scores_gemma":[0.000133547,0.0003474005,0.02120128,0.0001542884,0.00006858136,0.001000988,0.01861141,0.1092398,0.01964509,0.7959844,0.0335083,0.0001049513],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5875977,0.0002680879,0.2388864,0.005411417,0.0001539501,0.0001765736,0.00009725532,0.001073081,0.1663356],"genre_scores_gemma":[0.9855995,0.00004339228,0.01124523,0.0001389192,0.00001883623,0.00004146551,0.00002672067,0.0001226341,0.002763293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009322666,"threshold_uncertainty_score":0.03118747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02990772063665743,"score_gpt":0.36154815400059,"score_spread":0.3316404333639326,"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."}}