{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002874794,0.0002781699,0.0005709386,0.0002412572,0.0002076991,0.0006190254,0.002841262,0.0001907205,0.0002163922],"category_scores_gemma":[0.0002626595,0.0001734781,0.0001878354,0.0007460817,0.0000437515,0.0003317897,0.000277159,0.000214533,0.00004549427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001243602,"about_ca_system_score_gemma":0.000569163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001509545,"about_ca_topic_score_gemma":0.0002501154,"domain_scores_codex":[0.9973195,0.0004096946,0.0004321956,0.0008743464,0.0006636037,0.0003007071],"domain_scores_gemma":[0.9964892,0.0005132968,0.0004073261,0.002379966,0.000165687,0.00004450285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003573097,0.0002399723,0.00003314194,0.03446471,0.007006628,0.000002204423,0.003995491,0.8065464,0.0002241192,0.04452604,0.09846068,0.004464875],"study_design_scores_gemma":[0.000131682,0.00009742215,6.149066e-7,0.001233463,0.001329285,0.000001835493,0.00008629145,0.969531,0.00001448686,0.02660377,0.0007430199,0.0002271302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001317903,0.0003404508,0.9926314,0.0001490119,0.0003321299,0.001536473,0.00005224205,0.0003725593,0.004572591],"genre_scores_gemma":[0.008411686,0.0000188332,0.9449723,0.0001532584,0.0003721575,0.0005255001,0.0001232967,0.0002209023,0.04520204],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1629846,"threshold_uncertainty_score":0.7074233,"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."}}