{"id":"W6920767952","doi":"10.6084/m9.figshare.16869879","title":"Additional file 1 of Improve hot region prediction by analyzing different machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Support vector machine; Computational learning theory; Feature (linguistics); Feature selection; Statistical classification","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002294695,0.000104011,0.0001177854,0.00005389374,0.0001196341,0.00008203879,0.0002645923,0.00006148943,0.8137904],"category_scores_gemma":[0.003301047,0.00009991893,0.00006343747,0.0002475414,0.000004585559,0.0002538844,0.0001825665,0.0002503326,0.0002449486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003210957,"about_ca_system_score_gemma":0.00005448053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004628899,"about_ca_topic_score_gemma":0.000002343051,"domain_scores_codex":[0.999027,0.00007968221,0.0001874572,0.0003436185,0.0002246625,0.0001375725],"domain_scores_gemma":[0.9984464,0.0008204879,0.0002092726,0.0003149183,0.0001479489,0.00006098226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001017454,0.00004754067,0.00002575822,0.00002967153,0.000007456023,0.000003909198,0.00002174181,0.00001492012,0.000252941,0.000008093711,0.9640364,0.03555054],"study_design_scores_gemma":[0.0000881057,0.00005119487,0.003786883,0.0004093013,0.000002532716,0.00001215565,0.00000559367,0.2297215,0.0006578295,0.00001424189,0.7651618,0.00008886821],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00000446873,0.00008889519,0.004439156,0.0001123671,0.00003036078,0.00004468125,0.9945248,0.0001262426,0.000629028],"genre_scores_gemma":[0.002323081,0.000004609939,0.002656663,0.00003555887,0.00008289704,0.0001576383,0.9919327,0.000008465279,0.002798411],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8135455,"threshold_uncertainty_score":0.4074576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02098355276562209,"score_gpt":0.2273055492531494,"score_spread":0.2063219964875274,"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."}}