{"id":"W2765208928","doi":"10.1002/smr.1920","title":"Finding an effective classification technique to develop a software team composition model","year":2017,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Decision tree; Team composition; Machine learning; Software; Software development; Artificial intelligence; Logistic regression; Set (abstract data type); Data mining; Software engineering; Knowledge management","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":[],"consensus_categories":[],"category_scores_codex":[0.001094962,0.0001623441,0.0002268993,0.0003901762,0.0006062782,0.0004199362,0.001000025,0.000127637,0.000001298086],"category_scores_gemma":[0.003169799,0.0001510897,0.00003949141,0.0003563582,0.00005890291,0.002529358,0.0001774399,0.0003718583,0.000004674298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002899703,"about_ca_system_score_gemma":0.0003250552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006015101,"about_ca_topic_score_gemma":0.000001983888,"domain_scores_codex":[0.9985413,0.00006574216,0.0003317015,0.0002944805,0.0005069636,0.000259812],"domain_scores_gemma":[0.9972795,0.0002491779,0.0003812564,0.0004196026,0.001393996,0.0002764777],"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":[0.0007926916,0.001103522,0.31739,0.001683322,0.0002653385,0.0001220433,0.01470746,0.07228354,0.037079,0.00947821,0.00410748,0.5409874],"study_design_scores_gemma":[0.001359138,0.001083909,0.823036,0.00115586,0.00003528891,0.0008071097,0.0001193781,0.1419044,0.009191653,0.02032721,0.0001650317,0.0008150068],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1291655,0.00008055405,0.8698217,0.0002404099,0.0001874935,0.0003385955,0.000003607574,0.0001512752,0.00001086575],"genre_scores_gemma":[0.7380909,0.000006783759,0.2617049,0.00003102741,0.00008814625,0.00004827728,0.000001434813,0.00001295208,0.00001553697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6089255,"threshold_uncertainty_score":0.6161261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926189430131505,"score_gpt":0.3287277575982327,"score_spread":0.2994658632969177,"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."}}