{"id":"W4392940601","doi":"10.1101/2024.03.18.24304479","title":"A survey of experts to identify methods to detect problematic studies: Stage 1 of the INSPECT-SR Project","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Research for Patient Benefit Programme; National Institutes of Health; National Health and Medical Research Council; Department of Health and Social Care; National Institute for Health and Care Research; Scottish Government","keywords":"Transparency (behavior); Systematic review; Computer science; Process (computing); Inclusion (mineral); Psychological intervention; Health care; Best practice; Psychology; Data science; Medical education; MEDLINE; Medicine; Nursing; Social psychology; Political science; Computer security","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","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5553919,0.00304568,0.003596173,0.02092604,0.006636714,0.008968431,0.006400669,0.008205373,0.01273719],"category_scores_gemma":[0.6923588,0.004089936,0.004340234,0.009901854,0.005026227,0.01308215,0.01798647,0.008830682,0.008654657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01116385,"about_ca_system_score_gemma":0.0631428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003387918,"about_ca_topic_score_gemma":0.004755457,"domain_scores_codex":[0.4709356,0.3471067,0.1086484,0.01538778,0.05041295,0.00750846],"domain_scores_gemma":[0.1813304,0.4264839,0.06109846,0.05156567,0.2633799,0.01614168],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.002567356,0.001042339,0.02718595,0.03827412,0.0006805355,0.001526129,0.1918714,0.001430782,0.01376648,0.006855372,0.162181,0.5526184],"study_design_scores_gemma":[0.001853393,0.002312655,0.02871743,0.05067861,0.0009224347,0.001680688,0.06788751,0.008762878,0.009173873,0.01990336,0.8070511,0.001056118],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.11631,0.01074605,0.3960194,0.04377872,0.0039336,0.3893471,0.008093257,0.007170518,0.02460145],"genre_scores_gemma":[0.07024657,0.003685139,0.5717419,0.01660725,0.0007630566,0.3246691,0.00310715,0.001407891,0.007771996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9917946,"threshold_uncertainty_score":0.548281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8429969093959523,"score_gpt":0.6423196936438782,"score_spread":0.2006772157520741,"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."}}