{"id":"W4411793100","doi":"10.31234/osf.io/mvche_v1","title":"Flexible Behavior or Flexible Methods? A Cross-Taxon Review of Experimental Designs in Reversal Learning","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Austrian Science Fund; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Université Catholique de Louvain; European Commission; Leverhulme Trust; Open Philanthropy Project; National Science Foundation","keywords":"Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001638449,0.0005831551,0.001526206,0.0002346685,0.0001129472,0.00003987549,0.0007136819,0.0007457243,0.02690784],"category_scores_gemma":[0.0001747961,0.0004277731,0.0004720157,0.0005815913,0.0002679998,0.00005844682,0.00106676,0.001575157,0.0001241306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001494206,"about_ca_system_score_gemma":0.000101085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001487375,"about_ca_topic_score_gemma":0.00002673904,"domain_scores_codex":[0.9953868,0.001202752,0.001332321,0.001193148,0.000285421,0.000599582],"domain_scores_gemma":[0.9981576,0.0003399318,0.0004942307,0.0007556348,0.0001407474,0.0001118544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005366971,0.01525105,0.2283548,0.01857167,0.001053605,0.0007840313,0.006511723,0.00006114971,0.009851916,0.008046909,0.09804485,0.6081014],"study_design_scores_gemma":[0.01213043,0.007426622,0.398624,0.07315022,0.002754596,0.0001779388,0.007731572,0.00001704035,0.08382385,0.002343884,0.4042129,0.007606953],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.09224866,0.3686424,0.01257583,0.001152253,0.008255977,0.008642842,0.0002454206,0.001201065,0.5070356],"genre_scores_gemma":[0.1042214,0.04045425,0.1836604,0.005140553,0.0004814692,0.013141,0.0003253661,0.0001860655,0.6523895],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6004944,"threshold_uncertainty_score":0.9998174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5077044918703139,"score_gpt":0.5550947476409621,"score_spread":0.04739025577064826,"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."}}