{"id":"W2034942038","doi":"10.1002/spip.310","title":"Evaluation of a black‐box estimation tool: A case study","year":2007,"lang":"en","type":"article","venue":"Software Process Improvement and Practice","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Benchmarking; Estimation; Computer science; Outlier; White box; Black box; Set (abstract data type); Identification (biology); Software; Data science; Data mining; Industrial engineering; Software engineering; Artificial intelligence; Engineering; Systems engineering","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":[0.01974974,0.001009501,0.0007785707,0.002635948,0.0009891787,0.002546609,0.003967292,0.0021915,0.002588257],"category_scores_gemma":[0.0611282,0.000601258,0.0007477465,0.00273862,0.001633186,0.003571819,0.00208699,0.001409954,0.001126586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001615424,"about_ca_system_score_gemma":0.001752574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003342851,"about_ca_topic_score_gemma":0.003355403,"domain_scores_codex":[0.9810303,0.011072,0.001212787,0.001649428,0.004268435,0.0007669735],"domain_scores_gemma":[0.8927947,0.07528137,0.004165364,0.01288982,0.01307255,0.001796266],"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":[0.004887963,0.01229398,0.09616252,0.003498689,0.0005193389,0.008897671,0.02605118,0.1212622,0.03054438,0.02016396,0.01853654,0.6571816],"study_design_scores_gemma":[0.001188019,0.01386865,0.07410964,0.001901774,0.000556912,0.002936825,0.01943301,0.6993951,0.0888667,0.01088262,0.08634622,0.0005144963],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8969207,0.0004472437,0.0931382,0.0006759015,0.0000868924,0.001038678,0.000612164,0.002627323,0.004452798],"genre_scores_gemma":[0.8860027,0.0002018103,0.1089165,0.0001857753,0.00002621537,0.0006094606,0.001057148,0.0004776483,0.002522808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01974974,"threshold_uncertainty_score":0.1044479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0475530894494392,"score_gpt":0.3843926142398773,"score_spread":0.3368395247904381,"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."}}