{"id":"W6925097376","doi":"10.17605/osf.io/h8sn7","title":"WISEST Project: An AI tool to help assess the strengths and limitations of systematic reviews using ROBIS and AMSTAR-2","year":2018,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Ancient Mediterranean Archaeology and History","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Systematic review; Key (lock); Systematic error; Context (archaeology); Strengths and weaknesses","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":[0.1238685,0.004335438,0.007305623,0.05031903,0.002935719,0.009037708,0.003825332,0.002860461,0.04985318],"category_scores_gemma":[0.4507337,0.003310362,0.0110489,0.02260954,0.001988388,0.007960707,0.01270415,0.00262922,0.003887875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002929019,"about_ca_system_score_gemma":0.01877811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003379341,"about_ca_topic_score_gemma":0.01468637,"domain_scores_codex":[0.8847253,0.07102837,0.02934243,0.005897189,0.008068639,0.0009380261],"domain_scores_gemma":[0.3858911,0.5318876,0.03722596,0.01898459,0.0233291,0.002681679],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003675453,0.0003848229,0.02583054,0.3857754,0.04470792,0.00113028,0.01540331,0.003763883,0.005481575,0.04168989,0.1710325,0.3011243],"study_design_scores_gemma":[0.009995818,0.001642834,0.02730629,0.1019709,0.0991477,0.001565019,0.00967389,0.03465891,0.008843021,0.1078448,0.5958754,0.00147539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04730256,0.0276117,0.4398856,0.01769291,0.003619735,0.06891003,0.3128036,0.05401168,0.02816218],"genre_scores_gemma":[0.0288174,0.002421381,0.8813627,0.001085821,0.0002073462,0.06824049,0.01449252,0.001924749,0.001447595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8761315,"threshold_uncertainty_score":0.6550869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1275537405990421,"score_gpt":0.3165076083302796,"score_spread":0.1889538677312375,"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."}}