{"id":"W2015223621","doi":"10.1080/15434303.2014.981334","title":"Interpreting the Impact of the Ontario Secondary School Literacy Test on Second Language Students Within an Argument-Based Validation Framework","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Literacy; Context (archaeology); Mathematics education; Test (biology); Curriculum; Reading (process); Ell; Language proficiency; Empirical research; Psychology; Pedagogy; Language assessment; Linguistics; Teaching method; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002156588,0.0002811441,0.0002830522,0.00009695641,0.0004360736,0.0007812304,0.001259779,0.0001380839,0.0022243],"category_scores_gemma":[0.0002022937,0.0001712414,0.0002250081,0.0003708061,0.0001524563,0.0006747794,0.00007754562,0.000809064,0.00003803763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009341819,"about_ca_system_score_gemma":0.001193955,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03185959,"about_ca_topic_score_gemma":0.03417153,"domain_scores_codex":[0.9965785,0.0007991931,0.000483906,0.0003691439,0.001310989,0.0004583026],"domain_scores_gemma":[0.9977991,0.0005609579,0.0004945116,0.000758499,0.0001549533,0.0002319876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004974287,0.0005728125,0.5438338,0.000008453961,0.00009432029,0.00001074415,0.4514106,0.00004990556,0.0008062328,0.0002336612,0.0006054001,0.002324369],"study_design_scores_gemma":[0.001506245,0.002071383,0.7565621,0.0002743815,0.00007929908,0.000001321347,0.2376144,0.0002856197,0.0004860076,0.0005585418,0.0001667983,0.0003938935],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859685,0.00004082208,0.0001585789,0.0003260243,0.0005758933,0.0008030116,0.0000351297,0.0000722697,0.01201977],"genre_scores_gemma":[0.9961842,3.561883e-7,0.0008259438,0.0004821725,0.0002914397,0.00005246538,0.00004822072,0.0000272375,0.002087927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2137962,"threshold_uncertainty_score":0.9986878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646036534847547,"score_gpt":0.3890332495887422,"score_spread":0.3725728842402667,"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."}}