{"id":"W2929353344","doi":"10.1109/access.2019.2908032","title":"Enhancing Predictive Power of Cluster-Boosted Regression With Text-Based Indexing","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"King Mongkut's University of Technology Thonburi","keywords":"Computer science; Cluster analysis; Artificial intelligence; Search engine indexing; Bigram; Curse of dimensionality; Support vector machine; Word (group theory); Regression; Principal component analysis; Data mining; Machine learning; Regression analysis; Pattern recognition (psychology); Statistics; Mathematics; Trigram","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":[],"consensus_categories":[],"category_scores_codex":[0.0003680934,0.0001693619,0.0002549284,0.0001978249,0.00008390647,0.0001060966,0.001240396,0.00009865654,0.00004380686],"category_scores_gemma":[0.00006964802,0.0001253791,0.00004104082,0.0005587739,0.00003644225,0.0007623038,0.0002291737,0.0003510113,0.00001360173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000650136,"about_ca_system_score_gemma":0.0002108548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00022116,"about_ca_topic_score_gemma":0.00004803631,"domain_scores_codex":[0.9982343,0.0001867017,0.000300746,0.000471374,0.0005088213,0.0002980256],"domain_scores_gemma":[0.9982161,0.0003264454,0.0003514698,0.0007945774,0.0002196572,0.00009175095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005982051,0.0002097514,0.8760757,0.001087012,0.00007243676,0.00004835703,0.006084749,0.09174108,0.01102474,0.0009859937,0.0004037234,0.01166818],"study_design_scores_gemma":[0.002532148,0.001472525,0.1431544,0.002995575,0.00001538476,0.00002320841,0.0001386389,0.6997085,0.1487668,0.0002818137,0.0002810596,0.0006300018],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.653061,0.00003437933,0.3443492,0.0003817368,0.0004888712,0.000358689,0.000001916957,0.0001432449,0.001180936],"genre_scores_gemma":[0.9937103,6.976712e-7,0.005697862,0.0004126849,0.00003642702,0.00001476642,0.000001950511,0.0000193551,0.0001059002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7329214,"threshold_uncertainty_score":0.5112811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01354817976175746,"score_gpt":0.3062812843852586,"score_spread":0.2927331046235011,"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."}}