{"id":"W6963799178","doi":"10.24433/co.5422851.v1","title":"Applying the methodology of construction of weights and classification of texts from the article \"Weighting construction by bag-of-words with similarity-learning and supervised training for classification models in Court text documents\" in a set of data available on the internet","year":2022,"lang":"en","type":"other","venue":"Code Ocean","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Perceptron; Support vector machine; Word (group theory); Binary classification; Recall; Artificial neural network; Pattern recognition (psychology); Random forest; Training (meteorology)","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":[0.001419523,0.000123265,0.0003914398,0.000144416,0.00004182294,0.00000706015,0.0001552756,0.0001250386,0.0001280432],"category_scores_gemma":[0.0001566279,0.00007635545,0.00002359344,0.0002103771,0.0004077947,0.0000746858,0.00005289654,0.000286754,2.538585e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003508574,"about_ca_system_score_gemma":0.00007154071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003948614,"about_ca_topic_score_gemma":0.0001158969,"domain_scores_codex":[0.998479,0.0004187998,0.0004928993,0.0002788136,0.0002356518,0.00009481751],"domain_scores_gemma":[0.9977925,0.0009678287,0.0008069139,0.0003546681,0.00006336641,0.00001471449],"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":[0.001737955,0.0002066616,0.8463047,0.0007463811,0.000332058,5.558031e-7,0.01549427,0.00008794975,0.04339585,0.01016213,0.002114608,0.07941689],"study_design_scores_gemma":[0.01990297,0.002182235,0.1664575,0.008629209,0.003244022,0.00007579667,0.2145831,0.5207157,0.03964219,0.009433983,0.01414823,0.0009850779],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916555,0.0002760067,0.00445639,0.0002476288,0.00004889791,0.001449116,0.0003136258,0.00001023368,0.001542604],"genre_scores_gemma":[0.9951624,0.0001359481,0.003948836,0.00001312933,0.00001847056,0.00005659881,0.0004429953,0.00004135755,0.000180325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6798472,"threshold_uncertainty_score":0.3113685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1697088986960337,"score_gpt":0.3440660800343849,"score_spread":0.1743571813383512,"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."}}