{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006636239,0.00004044763,0.0000595275,0.00001684046,0.00007618891,0.00002823893,0.0005075037,0.00003549902,0.000005010287],"category_scores_gemma":[0.0007542767,0.00002059039,0.00002529256,0.0002223745,0.00002550572,0.0001374442,0.0001269021,0.0001169734,0.00001396766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001914445,"about_ca_system_score_gemma":0.00003004767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002300039,"about_ca_topic_score_gemma":0.00002872533,"domain_scores_codex":[0.9994609,0.00001730039,0.0001848832,0.0001209521,0.0001201475,0.00009579515],"domain_scores_gemma":[0.9986102,0.0007056176,0.00006256557,0.0005188031,0.00008387559,0.0000189207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003225701,0.0001724054,0.1637061,0.0001617986,0.00002950026,0.000005102853,0.005989985,0.00009347877,0.0666517,0.07545179,0.01518329,0.6725226],"study_design_scores_gemma":[0.001743138,0.0007716213,0.1633908,0.0001756364,0.00001340094,0.0001126512,0.0004062518,0.2348202,0.5488076,0.009727906,0.03933245,0.0006982934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8469439,0.00001543081,0.09735929,0.002496517,0.001427256,0.0001683234,5.202991e-7,0.0002582673,0.05133054],"genre_scores_gemma":[0.9772497,4.207134e-7,0.02237213,0.000180498,0.00005921206,0.000002197798,7.148125e-8,0.000001293575,0.0001344417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6718243,"threshold_uncertainty_score":0.09430766,"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."}}