{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0189474,0.000933944,0.0009040431,0.004188823,0.0008724703,0.009037059,0.002506461,0.001845298,0.01034795],"category_scores_gemma":[0.09537514,0.0004963739,0.0007212322,0.002520378,0.002536446,0.01180748,0.002976579,0.003547048,0.004656964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002262189,"about_ca_system_score_gemma":0.003956648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001663364,"about_ca_topic_score_gemma":0.004860588,"domain_scores_codex":[0.9878662,0.006348534,0.001042457,0.0007599823,0.003781899,0.0002009568],"domain_scores_gemma":[0.8975018,0.06251622,0.005582898,0.009031134,0.02327079,0.002097201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004371459,0.0001347646,0.001545039,0.0006228684,0.0000325881,0.0001283638,0.004039732,0.001047152,0.001680853,0.05954117,0.08987248,0.8413113],"study_design_scores_gemma":[0.0000485336,0.0002827015,0.003165414,0.002370741,0.0001401892,0.0007294107,0.004508565,0.007554366,0.006889341,0.2799943,0.6941234,0.0001929588],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02715224,0.02618568,0.7017567,0.0585605,0.01226417,0.001212409,0.001009221,0.009084146,0.1627749],"genre_scores_gemma":[0.1087268,0.007961706,0.8034367,0.004320576,0.001723539,0.0006232202,0.001029682,0.002777402,0.06940037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0189474,"threshold_uncertainty_score":0.1002046,"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."}}