{"id":"W3185590891","doi":"10.22034/elt.2021.43932.2334","title":"A New Dilemma for Language Teachers and Students: Self-assessment or Teacher Assessment (Research Article)","year":2021,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Dilemma; Self-assessment; Likert scale; Reading (process); Psychology; Reading comprehension; Mathematics education; Comprehension; Set (abstract data type); Test (biology); Medical education; Pedagogy; Computer science; 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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007030516,0.0003194946,0.0007288324,0.000461513,0.001110717,0.00488732,0.002732694,0.0001747223,0.01577714],"category_scores_gemma":[0.0004843574,0.000276856,0.0001961714,0.001449459,0.0002044006,0.002229186,0.001685834,0.0007027903,0.00001120683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000668944,"about_ca_system_score_gemma":0.001979529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00484219,"about_ca_topic_score_gemma":0.001894605,"domain_scores_codex":[0.9937382,0.001291362,0.0007736597,0.0006975421,0.002604685,0.0008945067],"domain_scores_gemma":[0.996657,0.001137499,0.0004261701,0.0004679523,0.0006732245,0.0006382255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001039576,0.001057632,0.8884072,0.00005068674,0.0005361791,0.00007867889,0.01158432,0.000004731796,0.008555352,0.001594481,0.06146584,0.02656092],"study_design_scores_gemma":[0.002036796,0.00004208317,0.9195396,0.0002038392,0.000172437,0.000003547386,0.02127017,0.00004998223,0.0008159699,0.002201537,0.05321947,0.0004445906],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746712,0.003955593,0.0006219186,0.001537528,0.000526458,0.001545732,0.00001747878,0.00007804611,0.01704608],"genre_scores_gemma":[0.9766451,0.006448271,0.006994335,0.0002499016,0.0007466052,0.0002112271,0.00001302312,0.00006647273,0.008625034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03113237,"threshold_uncertainty_score":0.9999683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3253825672241737,"score_gpt":0.6670082438301432,"score_spread":0.3416256766059695,"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."}}