{"id":"W6920948796","doi":"10.6084/m9.figshare.16869879.v1","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001751802,0.001647215,0.001506849,0.002241341,0.0009310485,0.002346714,0.00252086,0.001529676,0.8695974],"category_scores_gemma":[0.03632675,0.0006263251,0.001625247,0.003039771,0.0003534362,0.002291388,0.001252278,0.001418913,0.2877946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009398095,"about_ca_system_score_gemma":0.001706064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005614134,"about_ca_topic_score_gemma":0.01179253,"domain_scores_codex":[0.9990687,0.000162201,0.0001162172,0.0002991348,0.0002201369,0.0001337318],"domain_scores_gemma":[0.9742761,0.01969157,0.0006917225,0.001948219,0.002897496,0.0004948693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000413644,0.00008207271,0.00161579,0.001372759,0.00006192085,0.00005028837,0.00002500312,0.0005725781,0.0001364053,0.0004061008,0.9876842,0.007579227],"study_design_scores_gemma":[0.0105022,0.0006152444,0.02333406,0.002487887,0.0005622376,0.0009158873,0.0004366867,0.01072382,0.003735379,0.02455614,0.9218222,0.0003081961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.0002860459,0.00003053438,0.0006511402,0.0001219853,0.00005298815,0.00006121321,0.9967207,0.001260622,0.0008148362],"genre_scores_gemma":[0.009757607,0.0001193799,0.007323634,0.0005927792,0.0002148795,0.0009964488,0.96767,0.004089009,0.009236265],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8695974,"threshold_uncertainty_score":0.1860033,"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."}}