{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002344739,0.0006730336,0.0005708229,0.002908283,0.000744656,0.001514707,0.0008728427,0.0007903064,0.003932969],"category_scores_gemma":[0.0115697,0.0002981724,0.0008926701,0.002370343,0.0007754084,0.001663651,0.001032595,0.001337946,0.002767958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006876703,"about_ca_system_score_gemma":0.001167326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002063572,"about_ca_topic_score_gemma":0.003401319,"domain_scores_codex":[0.9974227,0.0009359343,0.0002380874,0.0005121039,0.0008182082,0.00007304665],"domain_scores_gemma":[0.9970112,0.001227489,0.0002643591,0.0005786935,0.0008643042,0.00005392749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001025091,0.0002439942,0.003245499,0.0002900292,0.0000740817,0.00006697737,0.0006321751,0.01533452,0.01376703,0.03204115,0.01284563,0.9213564],"study_design_scores_gemma":[0.00004380951,0.0002551182,0.007444688,0.0001586557,0.00007640339,0.0004181661,0.0005472086,0.7839046,0.05124072,0.08482245,0.07098353,0.0001046776],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01094174,0.00007800345,0.9847884,0.0001806486,0.0001035861,0.0002597946,0.0004032136,0.001255061,0.001989545],"genre_scores_gemma":[0.07285512,0.0001403098,0.9204804,0.00007593023,0.00008349714,0.0005572837,0.001757523,0.0002271933,0.003822705],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003932969,"threshold_uncertainty_score":0.01315713,"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."}}