{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01267991,0.0001432161,0.000138409,0.0001902204,0.000113005,0.0001479306,0.0002742619,0.00005210038,0.000007740563],"category_scores_gemma":[0.01859989,0.00013805,0.00002102376,0.0005980129,0.00003895178,0.001682284,0.0001724133,0.0001765645,0.000004590672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008953248,"about_ca_system_score_gemma":0.0002496322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001333481,"about_ca_topic_score_gemma":0.00002388362,"domain_scores_codex":[0.9973555,0.000150147,0.0003598527,0.0003911385,0.0014732,0.0002702161],"domain_scores_gemma":[0.9950467,0.00278235,0.0002181886,0.0004095112,0.001462118,0.00008106966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006086896,0.0006114529,0.004659407,0.0001982341,0.0001022049,0.0002111051,0.01141603,0.0008945608,0.0002483753,0.0001053757,0.00002642605,0.9814659],"study_design_scores_gemma":[0.02044694,0.01375432,0.04116839,0.0004244415,0.002546165,0.006646316,0.0591818,0.8005921,0.03298909,0.01817387,0.0007923862,0.0032842],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4960677,0.0001291175,0.5027755,0.00007414319,0.0000843029,0.0006994881,8.757138e-7,0.0001234141,0.00004550404],"genre_scores_gemma":[0.9429541,0.000004946708,0.05686921,0.00004782194,0.00002969579,0.00006626392,0.000001421558,0.00001190878,0.00001467447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9781818,"threshold_uncertainty_score":0.9896669,"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."}}