{"id":"W2965600044","doi":"10.1111/modl.12579","title":"Weighing Up Exercises on Phrasal Verbs: Retrieval Versus Trial‐and‐Error Practices","year":2019,"lang":"en","type":"article","venue":"Modern Language Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Victoria University of Wellington; University of Victoria","keywords":"Implementation; Meaning (existential); Computer science; Test (biology); Significant difference; Psychology; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008977864,0.0002218495,0.0003124075,0.0002098016,0.0002111287,0.0002440655,0.0002410325,0.000179648,0.06655109],"category_scores_gemma":[0.0005331681,0.0001875595,0.0001361905,0.000118634,0.00003507673,0.0003570526,0.00004791685,0.001004262,0.00110598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007091204,"about_ca_system_score_gemma":0.00004967587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004729778,"about_ca_topic_score_gemma":0.00000307007,"domain_scores_codex":[0.9980661,0.0003866436,0.0003549551,0.0003670154,0.0004043034,0.0004210338],"domain_scores_gemma":[0.9981986,0.000581329,0.000616543,0.0003603835,0.0000524914,0.0001905956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.4646684,0.00116178,0.0005358436,0.0001117146,0.00147306,0.006232032,0.2804788,0.0002595224,0.02337895,0.001823529,0.01471356,0.2051628],"study_design_scores_gemma":[0.4775627,0.01312033,0.009067459,0.0007123792,0.001208724,0.004720598,0.4130801,0.005260016,0.003011906,0.0005800866,0.06827061,0.003405169],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9648637,0.009462999,0.00015732,0.0003181126,0.00590067,0.0002544112,0.000005376759,0.00009004852,0.01894741],"genre_scores_gemma":[0.9878977,0.0000354919,0.0001741508,0.002600765,0.001637702,0.000004890931,0.00001032578,0.00005146044,0.007587518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2017576,"threshold_uncertainty_score":0.9996718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05336397463982574,"score_gpt":0.3910841418882373,"score_spread":0.3377201672484116,"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."}}