{"id":"W6891761735","doi":"10.48448/4th7-fj78","title":"Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Classifier (UML); Language model; Set (abstract data type); Task (project management); Quality (philosophy); Reliability (semiconductor); Language understanding","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":[0.01612144,0.001817896,0.0009143336,0.001514923,0.0007182587,0.002247479,0.00272352,0.001662316,0.002919731],"category_scores_gemma":[0.08631071,0.0006869206,0.0009414428,0.0006546776,0.001122151,0.002540782,0.003777182,0.00257576,0.002093256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001189434,"about_ca_system_score_gemma":0.001378741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00230015,"about_ca_topic_score_gemma":0.002770788,"domain_scores_codex":[0.9827271,0.01197349,0.0007289712,0.001906589,0.002189439,0.00047448],"domain_scores_gemma":[0.9194734,0.06501036,0.002182458,0.005695554,0.006122063,0.001516274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003491284,0.003176128,0.02444942,0.002859964,0.0003927816,0.001302219,0.0317792,0.07699504,0.06341552,0.007823801,0.01697599,0.7673387],"study_design_scores_gemma":[0.0005996507,0.003495201,0.01074207,0.0003392571,0.0001837219,0.0006272011,0.008406845,0.8815157,0.06910657,0.007702381,0.01692987,0.0003514212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6513193,0.0003684564,0.3254052,0.0004957785,0.0002928485,0.002151169,0.001097957,0.01233379,0.006535443],"genre_scores_gemma":[0.6845981,0.0001491094,0.3046555,0.000240583,0.00005495514,0.001348651,0.003727325,0.0007768472,0.004449109],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01612144,"threshold_uncertainty_score":0.08525932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1500237487525113,"score_gpt":0.416136112190019,"score_spread":0.2661123634375077,"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."}}