{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002332496,0.0006148088,0.0005590058,0.0005973731,0.0004461915,0.0007274366,0.001013573,0.0005470023,0.0001140246],"category_scores_gemma":[0.002480839,0.0005267379,0.0002279244,0.00106458,0.0001514217,0.000846651,0.0005221425,0.002030191,0.00003989151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008755021,"about_ca_system_score_gemma":0.0001370881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002207247,"about_ca_topic_score_gemma":0.000007097764,"domain_scores_codex":[0.9948127,0.0002785983,0.0008099944,0.001783656,0.001167782,0.001147308],"domain_scores_gemma":[0.994005,0.004630535,0.00010675,0.0008750715,0.0001434352,0.0002392639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001068024,0.0002834547,0.06131071,0.0003197055,0.0001257264,0.0002257671,0.004026176,0.824376,0.00008283364,0.001125055,0.000658392,0.1073593],"study_design_scores_gemma":[0.002189757,0.001068264,0.1729156,0.001541836,0.00007530296,0.0002555846,0.0004623721,0.8156916,0.00008242008,0.002129564,0.002317902,0.001269768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2368961,0.00103444,0.7577369,0.0006463259,0.001544889,0.001242411,0.00001368469,0.0008819621,0.000003284429],"genre_scores_gemma":[0.7409293,0.00006192763,0.2570025,0.000254564,0.000277848,0.001343594,0.00003002694,0.00007300943,0.00002723284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5040333,"threshold_uncertainty_score":0.9997184,"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."}}