{"id":"W3093772117","doi":"10.1145/3382494.3422159","title":"Beyond Accuracy","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Analytics; Data science; Software analytics; Software; Empirical research; Software engineering; Software development; Software development process","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":[],"consensus_categories":[],"category_scores_codex":[0.02538989,0.001994704,0.001855024,0.004561359,0.002444417,0.01620391,0.004698238,0.004619913,0.03738846],"category_scores_gemma":[0.2007741,0.0007650932,0.001232965,0.006216133,0.008005315,0.02572531,0.008727231,0.006725221,0.02147551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00484119,"about_ca_system_score_gemma":0.00573747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00640114,"about_ca_topic_score_gemma":0.002999087,"domain_scores_codex":[0.9543017,0.01298702,0.002997281,0.008738684,0.01953229,0.001442972],"domain_scores_gemma":[0.7816249,0.1388524,0.008832473,0.03590646,0.03211936,0.002664471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000203151,0.00006778447,0.009062421,0.002294102,0.0002017931,0.0001854096,0.0008726967,0.008744025,0.0007889216,0.5270082,0.09628543,0.354286],"study_design_scores_gemma":[0.00002410062,0.00005711652,0.002082685,0.002015356,0.00007868718,0.0004651441,0.000409343,0.01498001,0.001364086,0.7261722,0.252273,0.00007810551],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01196785,0.05895249,0.5577682,0.1385735,0.006613425,0.000341894,0.009004879,0.004116624,0.2126612],"genre_scores_gemma":[0.5326605,0.05024823,0.3058059,0.02956455,0.01466069,0.0007079918,0.01250008,0.003661796,0.05019018],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.03738846,"threshold_uncertainty_score":0.1342762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02822111614216395,"score_gpt":0.2775665520375836,"score_spread":0.2493454358954196,"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."}}