{"id":"W1985423220","doi":"10.1109/icpc.2010.9","title":"Visualizing the Results of Field Testing","year":2010,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada); Queen's University","funders":"","keywords":"Computer science; Field (mathematics); Software deployment; Visualization; Focus (optics); Variety (cybernetics); Test strategy; Process (computing); Data science; Software; Software engineering; Data mining; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006227911,0.001849854,0.0009363948,0.00725539,0.0006479013,0.003213511,0.0007980604,0.001046713,0.007170151],"category_scores_gemma":[0.0179258,0.0003448949,0.0007588302,0.003356192,0.0004434832,0.00198302,0.001195422,0.00124984,0.001421946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004832188,"about_ca_system_score_gemma":0.000494781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002417884,"about_ca_topic_score_gemma":0.002018556,"domain_scores_codex":[0.9974946,0.0009512427,0.0002640715,0.0002368752,0.0008932094,0.0001599602],"domain_scores_gemma":[0.97062,0.01693549,0.00221726,0.002910843,0.006542743,0.0007735494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003657721,0.0008131062,0.06931245,0.003282764,0.0005735334,0.002391564,0.02344021,0.03236949,0.0775248,0.01059015,0.07558342,0.7004607],"study_design_scores_gemma":[0.0007147761,0.004011168,0.2793262,0.002697456,0.001430779,0.005081614,0.01897144,0.3159858,0.163114,0.0348175,0.1727675,0.001081772],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4987606,0.004308393,0.3689199,0.004405386,0.0008834993,0.0008836251,0.01481504,0.05417731,0.05284617],"genre_scores_gemma":[0.7872701,0.001794121,0.1948581,0.0002969353,0.0002687105,0.0003486262,0.005166821,0.003018939,0.00697764],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00725539,"threshold_uncertainty_score":0.03293675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01990378391143411,"score_gpt":0.276366172521017,"score_spread":0.2564623886095829,"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."}}