{"id":"W4393372268","doi":"10.1109/ms.2024.3382364","title":"Toward Optimal Psychological Functioning in AI-Driven Software Engineering Tasks: The Software Evaluation for Well-Being and Optimal Psychological Functioning in a Context-Aware Environment Assessment Framework","year":2024,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Context (archaeology); Software engineering; Software development; Software; Psychological testing; Psychology; Clinical psychology; Programming language","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":[0.008432878,0.0007055525,0.0003882974,0.002645623,0.001086993,0.003197891,0.0005785716,0.0009225277,0.0008927036],"category_scores_gemma":[0.01875875,0.0002081072,0.0006454508,0.001155425,0.00305663,0.002712691,0.003600791,0.001594456,0.0001641776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001912973,"about_ca_system_score_gemma":0.002153194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001930237,"about_ca_topic_score_gemma":0.003110889,"domain_scores_codex":[0.9930767,0.004270391,0.0003042807,0.0004610305,0.001538274,0.0003493318],"domain_scores_gemma":[0.9907354,0.003702556,0.001662723,0.0007223562,0.001974019,0.001203045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006189021,0.002504489,0.4033606,0.0008526728,0.0003591731,0.0003819627,0.03604646,0.01163111,0.011101,0.1520928,0.005289463,0.3757614],"study_design_scores_gemma":[0.00009578993,0.002883191,0.7046961,0.0009414747,0.0002710581,0.0006316185,0.03195776,0.06656476,0.009247035,0.163588,0.01876483,0.0003583653],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7839263,0.001161332,0.1767163,0.003874312,0.00009235974,0.0006926241,0.0002080299,0.0002306864,0.03309811],"genre_scores_gemma":[0.9612083,0.0001769992,0.03757442,0.0001692229,0.0000101732,0.0003092168,0.00005355626,0.00001744564,0.000480641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008432878,"threshold_uncertainty_score":0.04459786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0358834102836699,"score_gpt":0.3324900582465691,"score_spread":0.2966066479628992,"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."}}