{"id":"W4221127326","doi":"10.31124/advance.19383266.v1","title":"Sadownik, S.A. (2022). Monitoring and Assessing Student Thinking in Google Math Classroom Environments.pdf","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Education and Cultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics education; Psychology; Computer science","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008737442,0.0001925728,0.000255841,0.00006906552,0.001314909,0.0005041395,0.0003709328,0.00013201,0.001793213],"category_scores_gemma":[0.00005078528,0.000177564,0.00005866684,0.0001330386,0.0001164635,0.0001939877,0.00131264,0.0006698591,0.00002900075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008746588,"about_ca_system_score_gemma":0.0001169692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003160602,"about_ca_topic_score_gemma":0.001103043,"domain_scores_codex":[0.9979451,0.000258726,0.0002829777,0.0004580237,0.0007340203,0.0003211827],"domain_scores_gemma":[0.9994861,0.00009471415,0.0001591657,0.0001622558,0.00001320191,0.00008454805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000002833586,0.0002589862,0.8088479,0.00004807714,0.00008549373,0.00001066732,0.165555,0.0001107785,0.0001537169,0.01198676,0.000751418,0.01218835],"study_design_scores_gemma":[0.000148097,0.000009564405,0.3957601,0.0000968507,0.00002531801,3.487038e-7,0.4716212,0.000006187278,0.00001801593,0.003331283,0.1286547,0.0003283179],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8787186,0.002755241,0.00001967864,0.00267865,0.002122705,0.000418541,0.000001950436,0.00006844252,0.1132162],"genre_scores_gemma":[0.9537554,0.005701953,0.001060278,0.0001478957,0.0004625055,0.0001803853,0.00001210027,0.0000159337,0.03866354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4130878,"threshold_uncertainty_score":0.9999852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04368475528973041,"score_gpt":0.3776834523097203,"score_spread":0.3339986970199899,"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."}}