{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08355575,0.001967732,0.002726393,0.02618065,0.001284585,0.006510425,0.002152033,0.001472281,0.006240673],"category_scores_gemma":[0.3104773,0.0007431089,0.003809154,0.01216922,0.000788843,0.003542256,0.002603063,0.0008803231,0.00159639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001865587,"about_ca_system_score_gemma":0.006298864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002615911,"about_ca_topic_score_gemma":0.005078572,"domain_scores_codex":[0.9403619,0.02825333,0.01904635,0.00491898,0.006963706,0.0004557444],"domain_scores_gemma":[0.5651491,0.3624282,0.0313903,0.01313384,0.02696257,0.0009360437],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002964608,0.0003841514,0.06326362,0.04853622,0.004143772,0.0004034959,0.003004189,0.003899844,0.01382623,0.002848212,0.008749232,0.8479764],"study_design_scores_gemma":[0.00647874,0.004761621,0.2547458,0.05174357,0.03589578,0.003343124,0.0104313,0.3259303,0.1152425,0.07158151,0.1184414,0.001404366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2175175,0.03022007,0.6917018,0.003182027,0.0007245495,0.02502353,0.01640557,0.007542534,0.007682369],"genre_scores_gemma":[0.2278112,0.002565438,0.7543674,0.0004550794,0.0001894978,0.008200035,0.005471098,0.0002414302,0.0006987487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9164442,"threshold_uncertainty_score":0.4418903,"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."}}