{"id":"W4386580855","doi":"10.2139/ssrn.4566951","title":"Using a Diagnostic Assessment to Determine Students’ Levels of Writing Knowledge","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Mathematics Education and Programs","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Writing assessment; Mathematics education; Psychology; Medical education; 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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006163196,0.0003769669,0.0007366371,0.0004073186,0.0001666987,0.0002009045,0.0009487892,0.0002098319,0.00007884764],"category_scores_gemma":[0.001942206,0.0003612407,0.0003057013,0.0003008495,0.00003370355,0.00005098638,0.000774833,0.002893715,0.00002910393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00158822,"about_ca_system_score_gemma":0.004829012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002123354,"about_ca_topic_score_gemma":0.0003273117,"domain_scores_codex":[0.9956344,0.0002621696,0.001247524,0.0003633791,0.0007128406,0.001779638],"domain_scores_gemma":[0.9963147,0.001626529,0.0009267464,0.0005396161,0.0004031918,0.0001892354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004807412,0.00520411,0.01983307,0.007180564,0.004411997,0.00004937073,0.02056602,0.0007008049,0.0009728252,0.8377191,0.001086608,0.1022274],"study_design_scores_gemma":[0.0004223027,0.0001870925,0.000758454,0.001831186,0.0003217254,0.0001716562,0.002986704,0.0009647233,0.0001046522,0.9917838,0.00006650192,0.0004012002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7880678,0.0007977455,0.2075584,0.0003412305,0.001184981,0.001222882,0.00002792826,0.0001178004,0.0006811631],"genre_scores_gemma":[0.953514,0.0006780687,0.04342107,0.00002243638,0.0006158956,0.00008179008,0.000005997286,0.0001375082,0.001523249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1654461,"threshold_uncertainty_score":0.9998839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2325303155525295,"score_gpt":0.4823400224216504,"score_spread":0.2498097068691209,"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."}}