{"id":"W3084911943","doi":"10.48550/arxiv.2009.06492","title":"Beyond Accuracy: ROI-driven Data Analytics of Empirical Data","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Analytics; Computer science; Data analysis; Data science; Data mining","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":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003945213,0.0003261985,0.0005369887,0.0001966476,0.0001089332,0.0001408318,0.01534702,0.0002371393,0.00003653626],"category_scores_gemma":[0.0004236405,0.000357856,0.0001163202,0.0008593696,0.0001343217,0.0007097583,0.03526768,0.001118679,0.00007658482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005286958,"about_ca_system_score_gemma":0.0004783457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002147215,"about_ca_topic_score_gemma":0.00003190207,"domain_scores_codex":[0.9967756,0.0002362386,0.0003221414,0.002139444,0.0002046991,0.0003219373],"domain_scores_gemma":[0.9911749,0.0003244519,0.0004805805,0.007643604,0.0001241478,0.0002523354],"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":[0.0001038437,0.0008197156,0.06011168,0.0008349384,0.001531718,0.002869129,0.001358045,0.7250382,0.00007048117,0.1076653,0.07703732,0.02255961],"study_design_scores_gemma":[0.0002794163,0.00004259696,0.001307926,0.00005024049,0.000136598,0.000004257923,0.00002586764,0.9825072,0.000009790456,0.009126837,0.006154746,0.0003544782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0125522,0.00007945644,0.9815708,0.001791255,0.000576293,0.0001945227,0.0006522046,0.0002683976,0.002314904],"genre_scores_gemma":[0.9721354,0.0001667576,0.0256379,0.0002430095,0.0002259393,1.106197e-7,0.001114764,0.00002240459,0.0004537263],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9595832,"threshold_uncertainty_score":0.9998873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.264585490832015,"score_gpt":0.2855492832822576,"score_spread":0.0209637924502426,"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."}}