{"id":"W4365511433","doi":"10.1017/s0958344023000071","title":"Beyond replication: An exact replication study of Łodzikowski (2021)","year":2023,"lang":"en","type":"article","venue":"ReCALL","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Replication (statistics); Computer science; Transcription (linguistics); Protocol (science); Linguistics; Mathematics; Statistics","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001109809,0.0000902238,0.0001756268,0.0001729176,0.0000710995,0.00001233471,0.0003822033,0.0001271329,0.001226339],"category_scores_gemma":[0.0001338437,0.00008852789,0.00003499042,0.000669679,0.00005800634,0.00004134041,0.00008719943,0.0001933931,0.001052817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002037712,"about_ca_system_score_gemma":0.00002968325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003864517,"about_ca_topic_score_gemma":0.00008909329,"domain_scores_codex":[0.9983174,0.0002588805,0.0003034289,0.0006712388,0.000191813,0.0002572001],"domain_scores_gemma":[0.9968351,0.0001528547,0.0001046658,0.002692433,0.000122151,0.00009281294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008443603,0.007837066,0.1366599,0.00006077764,0.0006136067,0.0001054932,0.06692085,0.00005379012,0.09144837,0.01603933,0.1572075,0.5222089],"study_design_scores_gemma":[0.0009163388,0.001521889,0.9747339,0.00000549383,0.00002061742,0.00001194,0.001474696,0.0002537803,0.001489685,0.005541203,0.01387274,0.0001577281],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714102,0.0000692194,0.00001924545,0.0006897742,0.0002482104,0.0004787288,0.00001242503,0.00008271652,0.02698951],"genre_scores_gemma":[0.9921635,0.00004314943,0.00004606055,0.00005169085,0.0001328369,0.00018463,0.00008397863,0.00002149104,0.007272643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.838074,"threshold_uncertainty_score":0.999725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08677049804674758,"score_gpt":0.4295550927112266,"score_spread":0.342784594664479,"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."}}