{"id":"W4383196665","doi":"10.21203/rs.3.rs-3126005/v1","title":"Artificial Intelligence versus Software Engineers: An Evidence-Based Assessment Focusing on Non-Functional Requirements","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software engineering; Workflow; Software development; Artificial intelligence; Software; Database","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2493031,0.0009144033,0.003347144,0.0204701,0.001879631,0.01055985,0.004445635,0.005175812,0.005510915],"category_scores_gemma":[0.5683724,0.0008948104,0.004150249,0.0137247,0.004275021,0.009938975,0.006544952,0.004255912,0.0009986393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004657567,"about_ca_system_score_gemma":0.0064352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001253889,"about_ca_topic_score_gemma":0.002926376,"domain_scores_codex":[0.7645168,0.1045088,0.06691695,0.008368549,0.05388157,0.001807391],"domain_scores_gemma":[0.1604619,0.7147008,0.0632262,0.01084438,0.04765988,0.003106942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005667882,0.00193574,0.2409284,0.1781853,0.01824467,0.0005429099,0.01726032,0.0009741681,0.001231256,0.01199033,0.009491823,0.5135472],"study_design_scores_gemma":[0.002654139,0.0154506,0.2846234,0.4972178,0.04084481,0.002983137,0.04232791,0.006034182,0.004089105,0.02074618,0.08243622,0.0005925801],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4452298,0.4214027,0.03490947,0.05166725,0.002210308,0.01228346,0.004077293,0.0001387322,0.02808105],"genre_scores_gemma":[0.9078993,0.0548261,0.02407387,0.006569772,0.0004763874,0.004594962,0.001105978,0.00003931602,0.0004143385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2493031,"threshold_uncertainty_score":0.925743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7657607625549739,"score_gpt":0.6044798249884009,"score_spread":0.161280937566573,"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."}}