{"id":"W4390929439","doi":"10.1098/rsos.231003","title":"Replicability of simulation studies for the investigation of statistical methods: the RepliSims project","year":2024,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; York University","funders":"Leids Universitair Medisch Centrum; ZonMw","keywords":"Computer science; Replication (statistics); Code (set theory); Data science; Visualization; Empirical research; Information retrieval; Data mining; Statistics; Programming language","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06907332,0.00008309833,0.0002157065,0.00004607442,0.00073563,0.0009456281,0.00337855,0.00002111165,0.00001989675],"category_scores_gemma":[0.02861085,0.00003668113,0.0001284232,0.002460327,0.002661526,0.0003856057,0.001997586,0.00008578672,0.000003637896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000593686,"about_ca_system_score_gemma":0.0003493023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000213756,"about_ca_topic_score_gemma":0.00001034532,"domain_scores_codex":[0.9963518,0.0003207853,0.0007219566,0.0009291429,0.001483492,0.0001927858],"domain_scores_gemma":[0.9672518,0.02930949,0.0003213148,0.002049347,0.001026181,0.0000418442],"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":[0.00004829117,0.000063507,0.001706198,0.0001731536,0.0001313641,2.241613e-7,0.0306013,0.1126577,0.001516355,0.07053258,0.1636951,0.6188741],"study_design_scores_gemma":[0.00006027815,0.00004958942,0.007721351,0.00002785166,0.0000276684,1.670364e-7,0.00776808,0.9202933,0.0006593573,0.04829963,0.01503986,0.00005281633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03141095,0.000438794,0.9618957,0.003025904,0.0009550991,0.001691142,0.00007967672,0.0000261043,0.0004765998],"genre_scores_gemma":[0.8821045,0.000006334448,0.1167753,0.0001530367,0.00003670775,0.00005357643,0.000002832313,0.000003729783,0.0008640278],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8506935,"threshold_uncertainty_score":0.9806505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3958113089703145,"score_gpt":0.5803904642367242,"score_spread":0.1845791552664098,"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."}}