{"id":"W3144668312","doi":"","title":"Evaluating the evaluator:modelling systematic data analysis strategies for software selection","year":2004,"lang":"en","type":"other","venue":"NPARC","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Variety (cybernetics); Software engineering; Software; Software construction; Software development; Selection (genetic algorithm); Data science; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3014514,0.003545091,0.003864793,0.01189489,0.002295175,0.009462511,0.005352245,0.004179887,0.004457317],"category_scores_gemma":[0.6523327,0.002113896,0.004348197,0.009193568,0.007563659,0.01636931,0.005900734,0.003619742,0.0009686411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007209886,"about_ca_system_score_gemma":0.01940244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007108067,"about_ca_topic_score_gemma":0.01096237,"domain_scores_codex":[0.5665323,0.3955087,0.01149879,0.007753065,0.01756123,0.001145923],"domain_scores_gemma":[0.2043329,0.7448601,0.01342788,0.01818776,0.01831643,0.0008751049],"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":[0.001435332,0.0007053259,0.02657991,0.008076291,0.002122785,0.0003766534,0.02045629,0.07188331,0.001046318,0.2103106,0.005591162,0.6514161],"study_design_scores_gemma":[0.001109789,0.00159172,0.00501735,0.006397224,0.001311897,0.0002314626,0.004280112,0.4890465,0.00264846,0.4735389,0.01454468,0.0002820176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0117067,0.001731116,0.9772127,0.001256051,0.00005274331,0.004200146,0.0003253026,0.0003942326,0.003121032],"genre_scores_gemma":[0.09639102,0.001060793,0.893113,0.0003155076,0.00005102313,0.007800158,0.0003698309,0.0001376764,0.0007609859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3014514,"threshold_uncertainty_score":0.8614348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1836313259989212,"score_gpt":0.3833890664917619,"score_spread":0.1997577404928406,"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."}}