{"id":"W2915455637","doi":"10.15626/mp.2018.843","title":"A Brief Guide to Evaluate Replications","year":2019,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Replication (statistics); Transparency (behavior); Independence (probability theory); Computer science; Similarity (geometry); Research design; Psychology; Statistics; Artificial intelligence; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.1272678,0.0003035868,0.004216787,0.0005475528,0.00009063977,0.000318553,0.002883065,0.0001146175,0.1438041],"category_scores_gemma":[0.02839296,0.0001437781,0.002519505,0.002094109,0.00004468581,0.0001325465,0.0001885429,0.0001528961,0.18516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001783192,"about_ca_system_score_gemma":0.00004458729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001586258,"about_ca_topic_score_gemma":0.00002709265,"domain_scores_codex":[0.9754149,0.01016772,0.00841983,0.002148402,0.003450798,0.0003983247],"domain_scores_gemma":[0.9815844,0.00210902,0.002381533,0.01237196,0.001309111,0.0002440127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006619124,0.00005388484,0.004139873,0.000004398082,0.001076933,0.000002185167,0.0001223054,0.00004975092,0.001091133,0.004553144,0.9656626,0.02323717],"study_design_scores_gemma":[0.00019003,0.00006159129,0.03375987,0.000001886853,0.001091104,0.00002672239,0.00002549924,0.0002413702,0.00002047161,0.007166452,0.9572689,0.0001460868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.09121804,0.002328424,0.1187117,0.05806079,0.001858036,0.003226637,0.00004320297,0.00003735765,0.7245158],"genre_scores_gemma":[0.3258395,0.00004037352,0.06468218,0.06392372,0.0002390996,0.0008322992,0.00001922018,0.00005082922,0.5443729],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2346214,"threshold_uncertainty_score":0.9797913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8534897186781798,"score_gpt":0.6528829468946589,"score_spread":0.2006067717835209,"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."}}