{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004357325,0.0004056634,0.0004861919,0.001286505,0.0005861567,0.0002878529,0.0004186447,0.0006056231,0.0004654081],"category_scores_gemma":[0.005754204,0.0004019061,0.0002505421,0.0009865953,0.0002335643,0.0002713011,0.0003177203,0.002961516,0.000844445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002678839,"about_ca_system_score_gemma":0.00555417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001916153,"about_ca_topic_score_gemma":0.000245991,"domain_scores_codex":[0.9931127,0.0005117317,0.0009520084,0.001278065,0.003098977,0.001046563],"domain_scores_gemma":[0.9929765,0.003137943,0.0001801507,0.001348658,0.001728392,0.0006283247],"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":[0.009818329,0.003196047,0.0151302,0.007554016,0.0003889331,0.0003958233,0.003429529,0.05748912,0.001554727,0.002218616,0.005344442,0.8934802],"study_design_scores_gemma":[0.0006180494,0.03610797,0.08929822,0.1003951,0.0006898838,0.00001784548,0.04384242,0.4604302,0.182643,0.08011387,0.001599093,0.004244386],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7520484,0.0005258258,0.1953124,0.02492252,0.01699895,0.008424105,0.0001394782,0.001112204,0.0005161766],"genre_scores_gemma":[0.9892743,0.0002969358,0.004563035,0.0001558907,0.003727183,0.0008012429,0.000877048,0.000116664,0.0001876863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8892359,"threshold_uncertainty_score":0.9999335,"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."}}