{"id":"W4251856847","doi":"10.26434/chemrxiv.13119869.v2","title":"Reasoning, granularity, and comparisons in students’ arguments on two organic chemistry items","year":2021,"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; Mathematics education; Epistemology; Work (physics); Psychology; Computer science; Chemistry; Philosophy; Engineering","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":[0.001213526,0.0001884484,0.0002997669,0.00006529619,0.0003136448,0.0005102122,0.0007037259,0.0002559917,0.001932558],"category_scores_gemma":[0.0005204415,0.0002134024,0.00005965572,0.0003309947,0.0002868988,0.00007205398,0.0004540065,0.0007971828,0.00002772641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002430206,"about_ca_system_score_gemma":0.0007214588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003087815,"about_ca_topic_score_gemma":0.003242418,"domain_scores_codex":[0.9979476,0.0001822318,0.0002528426,0.0006246669,0.0006397791,0.0003529194],"domain_scores_gemma":[0.9990421,0.0001128545,0.0001532982,0.0003805342,0.00008512678,0.0002260779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006383209,0.0005660488,0.9529757,0.00006776927,0.00002765791,0.00001418403,0.04210797,0.00001124568,0.001080625,0.0004709929,0.002114235,0.0005571468],"study_design_scores_gemma":[0.002729001,0.00003751338,0.7554747,0.0016469,0.0001083744,0.000009043087,0.1460654,0.0002458979,0.01228194,0.002792254,0.07646944,0.002139579],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770492,0.0003397077,0.00001419687,0.001467434,0.0009678456,0.0002129556,0.000001209391,0.00004403188,0.0199034],"genre_scores_gemma":[0.9950662,0.0003309309,0.0001124796,0.0002545129,0.000315432,0.00003423016,0.00003613567,0.00001238726,0.003837669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.197501,"threshold_uncertainty_score":0.9989798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06564638008075757,"score_gpt":0.4143310449054456,"score_spread":0.348684664824688,"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."}}