{"id":"W2886527588","doi":"10.1002/jrsm.1317","title":"Discriminating between empirical studies and nonempirical works using automated text classification","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal; Computer Research Institute of Montréal","funders":"Medical Research Council","keywords":"Computer science; Empirical research; Natural language processing; Artificial intelligence; Statistics; Mathematics","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":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4401701,0.0003258007,0.003437842,0.001144808,0.001033398,0.001570636,0.001535217,0.0002189334,0.001051403],"category_scores_gemma":[0.4740036,0.0001609347,0.0006206417,0.003915394,0.001126837,0.0004099004,0.0007363214,0.0004804234,0.0006497343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001676258,"about_ca_system_score_gemma":0.0001361761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001353162,"about_ca_topic_score_gemma":0.00000853711,"domain_scores_codex":[0.8615221,0.1226365,0.00616232,0.001729327,0.007160313,0.0007894357],"domain_scores_gemma":[0.7562681,0.2299128,0.002598333,0.00454509,0.006069971,0.0006056702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001220799,0.00004747498,0.05607339,0.0001151428,0.0004786976,0.000003830904,0.002214727,0.000003999419,0.003831974,0.0003298352,0.01463166,0.9222571],"study_design_scores_gemma":[0.0001874087,0.0001648381,0.2766927,0.0007677636,0.0007091716,0.00002368213,0.02196007,0.6497641,0.004450294,0.02035927,0.02429006,0.0006306932],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5491386,0.003017892,0.4356228,0.005549714,0.0002121256,0.001090476,0.000008080411,0.00007497077,0.005285339],"genre_scores_gemma":[0.5791526,0.00005012026,0.4199482,0.00003267878,0.0003000227,0.00005441815,6.264157e-7,0.00001918104,0.0004422032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9216264,"threshold_uncertainty_score":0.9998618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9826945330606024,"score_gpt":0.7893720715156879,"score_spread":0.1933224615449145,"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."}}