{"id":"W2078446277","doi":"10.1016/j.knosys.2010.07.008","title":"Advanced empirical testing","year":2010,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science","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":[0.04613418,0.001940671,0.001848471,0.003260103,0.001894288,0.003018868,0.004047412,0.001773676,0.1010752],"category_scores_gemma":[0.2583534,0.000630744,0.003008875,0.002969262,0.003198612,0.008553077,0.00367413,0.00300886,0.01708838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260127,"about_ca_system_score_gemma":0.003743332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001554365,"about_ca_topic_score_gemma":0.001634064,"domain_scores_codex":[0.9492888,0.02870183,0.00391601,0.007010317,0.009460825,0.001622153],"domain_scores_gemma":[0.5727507,0.3263488,0.007768195,0.05847721,0.03228166,0.002373506],"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":[0.002616339,0.003289567,0.05991658,0.003003107,0.001544672,0.001118822,0.003435236,0.006883958,0.005221733,0.2784873,0.05566276,0.5788199],"study_design_scores_gemma":[0.00269594,0.005782755,0.104734,0.002755599,0.002350616,0.002556192,0.008948582,0.06342296,0.01211818,0.582115,0.2122927,0.0002275614],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1511592,0.002176149,0.5494957,0.009516047,0.001754423,0.004133945,0.00831113,0.002186503,0.271267],"genre_scores_gemma":[0.7923365,0.0009214441,0.162948,0.002792006,0.0007677223,0.004329333,0.006127476,0.0004887035,0.02928883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1010752,"threshold_uncertainty_score":0.3381303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03136029153661333,"score_gpt":0.2997289248272138,"score_spread":0.2683686332906005,"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."}}