{"id":"W2898388844","doi":"10.1007/978-3-319-92390-1_43","title":"Re-Framing Testing to Better Fit Within Problem-solving Classrooms: Ways to Create and Review Tests","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in mathematics education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Lethbridge; York University","funders":"","keywords":"Mathematics education; Framing (construction); Underpinning; Pencil (optics); Test (biology); Psychology; Pedagogy; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001306172,0.0002937514,0.000440672,0.0002059061,0.0002738397,0.0001464399,0.0003571362,0.0001453335,0.0002999687],"category_scores_gemma":[0.001333075,0.0002867242,0.00004155968,0.0002215114,0.0001157013,0.0003842509,0.0001329341,0.000230653,0.0001598379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002940291,"about_ca_system_score_gemma":0.0002762262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004748411,"about_ca_topic_score_gemma":0.001502878,"domain_scores_codex":[0.9980274,0.00002874483,0.0006669444,0.0004570952,0.0005013685,0.0003184117],"domain_scores_gemma":[0.998157,0.000609129,0.0004900398,0.0003151247,0.0002812912,0.0001474509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001214049,0.0004861316,0.01189301,0.01563127,0.0001031563,0.00000793668,0.3193472,0.0000294801,0.00007893,0.3685646,0.03521763,0.2486285],"study_design_scores_gemma":[0.0001354168,0.0001528439,0.0003753983,0.05807851,0.0001754892,0.00000270452,0.01048394,0.0000306791,0.000005923953,0.5279818,0.4015291,0.00104829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001120319,0.01025882,0.001018495,0.002132371,0.0007278248,0.002672025,0.000004431728,0.00009074828,0.981975],"genre_scores_gemma":[0.001584748,0.01294759,0.7595005,0.003869908,0.001877197,0.0004704934,0.00002424301,0.0001593479,0.219566],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.762409,"threshold_uncertainty_score":0.9999585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05781820994205484,"score_gpt":0.3800965022162223,"score_spread":0.3222782922741675,"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."}}