{"id":"W6958291173","doi":"10.6084/m9.figshare.15179120","title":"Additional file 2 of Creating efficiencies in the extraction of data from randomized trials: a prospective evaluation of a machine learning and text mining tool","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Information extraction; Extraction (chemistry); Data extraction; Text mining; Training set","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01907269,0.001572773,0.002413741,0.006047473,0.0009588357,0.003095197,0.002985461,0.001724203,0.8421819],"category_scores_gemma":[0.2480363,0.001330333,0.002992339,0.00709609,0.0006094365,0.003096611,0.002238404,0.001536598,0.07785271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002127867,"about_ca_system_score_gemma":0.005681355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003031155,"about_ca_topic_score_gemma":0.005911789,"domain_scores_codex":[0.9913875,0.003140499,0.002901409,0.001068422,0.001152011,0.0003501162],"domain_scores_gemma":[0.5903003,0.369763,0.01393329,0.009957275,0.01423175,0.001814311],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003378853,0.000290704,0.004324814,0.04519208,0.000795328,0.0001904612,0.0002975326,0.001609195,0.000332354,0.003222132,0.8972008,0.04316583],"study_design_scores_gemma":[0.06725435,0.001786794,0.03226596,0.02491658,0.004027978,0.001254509,0.0007153317,0.01350571,0.004333973,0.04607965,0.8032011,0.0006581045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.0005937835,0.00008310422,0.003771561,0.0004153965,0.00008441598,0.002258891,0.9894449,0.001940801,0.001407112],"genre_scores_gemma":[0.03230527,0.0007374181,0.1230087,0.002512139,0.0006269772,0.1006032,0.7076488,0.007450848,0.02510657],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9809273,"threshold_uncertainty_score":0.2251083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8256885907417781,"score_gpt":0.5555753573035008,"score_spread":0.2701132334382773,"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."}}