{"id":"W4411629503","doi":"10.1080/09500693.2025.2517889","title":"Science teacher's assessment of their students’ models","year":2025,"lang":"en","type":"article","venue":"International Journal of Science Education","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Agenția Națională pentru Cercetare și Dezvoltare","keywords":"Mathematics education; Science education; Psychology; Pedagogy","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"],"consensus_categories":[],"category_scores_codex":[0.008752692,0.00007215963,0.0001221897,0.001979609,0.0006545378,0.0004038144,0.003471217,0.00003174605,0.0001507859],"category_scores_gemma":[0.001208483,0.00006139281,0.00006414407,0.002697345,0.003845375,0.002426807,0.0001255765,0.0001814157,0.000002279628],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009812984,"about_ca_system_score_gemma":0.04694682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003606844,"about_ca_topic_score_gemma":0.00005552989,"domain_scores_codex":[0.9963305,0.0001000676,0.000471562,0.000205098,0.002663467,0.0002293115],"domain_scores_gemma":[0.9944867,0.0001309264,0.0005195545,0.0001678764,0.004526814,0.0001680908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000127474,0.00111522,0.07925428,0.000003673073,0.00002286638,3.803011e-7,0.03377194,0.0003905644,0.01283299,0.8009583,0.001409138,0.0702279],"study_design_scores_gemma":[0.0006782885,0.0001799162,0.5081046,0.0004377688,0.00003419539,0.00002062044,0.3351271,0.002554679,0.007153316,0.103071,0.04230921,0.0003292559],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8773575,0.00008169812,0.002858871,0.00828544,0.01176959,0.0001106247,0.000001125088,0.000007432464,0.09952774],"genre_scores_gemma":[0.9946775,0.0001081081,0.002363379,0.0003748247,0.0003821976,0.000002736334,3.740219e-7,0.000002025495,0.002088789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6978873,"threshold_uncertainty_score":0.9988656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06498519127119523,"score_gpt":0.5280203661313481,"score_spread":0.4630351748601528,"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."}}