{"id":"W4250126307","doi":"10.26434/chemrxiv.13119869","title":"Reasoning, granularity, and comparisons in students’ arguments on two organic chemistry items","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Argumentation theory; Granularity; Chemistry; Mathematics education; Psychology; Epistemology; Computer science; Philosophy","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009231715,0.0001939965,0.0002986725,0.00005612835,0.0002879123,0.0003302234,0.0008360631,0.0002281851,0.001175946],"category_scores_gemma":[0.0005588194,0.0002155373,0.00005436884,0.0003185571,0.0002944589,0.00005750229,0.0004522053,0.0008584424,0.0000785953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000205845,"about_ca_system_score_gemma":0.0005313858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002068859,"about_ca_topic_score_gemma":0.001138512,"domain_scores_codex":[0.9980187,0.0001467615,0.0002520493,0.000626497,0.0006255385,0.0003304837],"domain_scores_gemma":[0.9990842,0.0001050803,0.0001630475,0.0003005844,0.00005274201,0.0002943462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001589096,0.0004566809,0.9377832,0.00009367199,0.00003201756,0.00001179927,0.05025045,0.000009562054,0.001378385,0.001536886,0.007845549,0.0005858442],"study_design_scores_gemma":[0.003685586,0.00007841757,0.6691108,0.001251223,0.0001360433,0.000005607671,0.07215863,0.0005551868,0.009668022,0.01523002,0.225452,0.002668435],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685912,0.0001666726,0.00001901682,0.005069769,0.0007877466,0.0002861104,0.000002227019,0.00006862867,0.02500865],"genre_scores_gemma":[0.9966768,0.000197611,0.00009680665,0.0004609493,0.0004296044,0.00003301307,0.00002553182,0.00001352775,0.002066179],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2686725,"threshold_uncertainty_score":0.9997371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08853200618493173,"score_gpt":0.4210660436723305,"score_spread":0.3325340374873987,"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."}}