{"id":"W4248747928","doi":"10.26434/chemrxiv.13119869.v1","title":"Reasoning, Granularity, and Comparisons: A Unit-Based Method for Characterizing Students’ Arguments on Chemistry Assessments","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Rubric; Argumentation theory; Granularity; Argument (complex analysis); Mathematics education; Unit (ring theory); Computer science; Qualitative reasoning; Epistemology; Psychology; Management science; Artificial intelligence; Chemistry; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02909895,0.001253707,0.001128857,0.01236768,0.001971395,0.00605347,0.00196813,0.001447966,0.01188627],"category_scores_gemma":[0.1804662,0.0006774508,0.001338692,0.008833062,0.002203336,0.003869192,0.004933597,0.002763264,0.001964887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002099128,"about_ca_system_score_gemma":0.00217208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001344221,"about_ca_topic_score_gemma":0.002983053,"domain_scores_codex":[0.9474962,0.03429316,0.005483294,0.003750828,0.008244617,0.0007319304],"domain_scores_gemma":[0.771226,0.1807966,0.01187222,0.01443871,0.01987349,0.001793006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002511506,0.001266195,0.0493848,0.0024735,0.0004501723,0.0004411908,0.06701933,0.003443301,0.02114112,0.04752286,0.01438081,0.7899653],"study_design_scores_gemma":[0.001608674,0.003245516,0.1946113,0.002520843,0.0007382692,0.001345811,0.06343285,0.2161643,0.06648737,0.229121,0.2194869,0.001237101],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2204758,0.000487095,0.7362632,0.0006061154,0.0003623292,0.01011373,0.003051689,0.00300969,0.02563039],"genre_scores_gemma":[0.178801,0.0001008771,0.805363,0.0001172565,0.0000481228,0.01108466,0.001413597,0.0003702944,0.002701104],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02909895,"threshold_uncertainty_score":0.1538917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1390204220203705,"score_gpt":0.4871178097378093,"score_spread":0.3480973877174389,"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."}}