{"id":"W4402581411","doi":"10.3758/s13428-024-02508-y","title":"A standardized framework to test event-based experiments","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Templeton World Charity Foundation","keywords":"Computer science; Protocol (science); Snapshot (computer storage); Replication (statistics); Robustness (evolution); Benchmark (surveying); Medical physics; Data science; Cognitive psychology; Psychology; Medicine","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":[],"category_scores_codex":[0.005997363,0.0002048691,0.0002595309,0.0005931311,0.0005267588,0.0003792323,0.0004561316,0.0001060105,0.0005739014],"category_scores_gemma":[0.09652898,0.0001820805,0.0001489658,0.00214986,0.0002319168,0.0001590394,0.0004097616,0.000869595,0.0004506799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004245228,"about_ca_system_score_gemma":0.0003723662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003368026,"about_ca_topic_score_gemma":0.000004484597,"domain_scores_codex":[0.9938793,0.002497094,0.0002555642,0.001037308,0.001584744,0.0007459787],"domain_scores_gemma":[0.9518988,0.04700941,0.00001781086,0.0005915264,0.0001972038,0.000285237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001194714,0.0004519324,0.0004416434,0.00003936966,0.000007595002,0.0002521875,0.0005129089,0.00002395874,0.9336652,0.002765347,0.00966223,0.05205822],"study_design_scores_gemma":[0.0002264765,0.0006747427,0.0008935827,0.0001577045,0.00001055466,0.00000906379,0.0001870178,0.0004764728,0.8782618,0.002204744,0.1166734,0.00022441],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3412773,0.001320703,0.6219174,0.02278452,0.003673093,0.004223883,0.0003596519,0.001260062,0.003183376],"genre_scores_gemma":[0.7571951,0.00001503779,0.2353415,0.001334185,0.0002897743,0.00315975,0.000001842318,0.00009902411,0.002563713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4159179,"threshold_uncertainty_score":0.9110813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4266002189805213,"score_gpt":0.6289628346652205,"score_spread":0.2023626156846993,"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."}}