{"id":"W3207255984","doi":"10.1093/reseval/rvab029","title":"Teachers conceptualizing and developing assessment for skill development: Trialing a maker assessment framework","year":2021,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Creativity; Context (archaeology); Knowledge management; Computer science; Psychology; Engineering ethics; Social psychology; 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":[],"consensus_categories":[],"category_scores_codex":[0.02259674,0.0001374913,0.0001954168,0.0002062896,0.001034864,0.0009262152,0.0003125434,0.0001188633,0.00001717449],"category_scores_gemma":[0.003974542,0.0001392622,0.00004651766,0.0005967722,0.00005536058,0.0003638169,0.0003261991,0.0007055028,0.000004839176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007562939,"about_ca_system_score_gemma":0.00257167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000144149,"about_ca_topic_score_gemma":0.000008236074,"domain_scores_codex":[0.9946761,0.002116215,0.0003676133,0.0006461594,0.001614055,0.0005798743],"domain_scores_gemma":[0.9966028,0.001881394,0.0001098669,0.0003455949,0.0009392488,0.0001210492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004219202,0.00004243104,0.000903522,0.00004372428,0.00004965489,0.000003620876,0.01396181,0.0002688616,0.0003201334,0.06829386,0.00008382164,0.9160243],"study_design_scores_gemma":[0.005708032,0.0003837921,0.04919384,0.001863862,0.0000704214,0.00003968926,0.01506745,0.5005028,0.003050082,0.03774104,0.3851132,0.001265803],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04864611,0.0005426143,0.9469962,0.00247381,0.0002674111,0.0007091129,4.030236e-7,0.0001123991,0.0002519946],"genre_scores_gemma":[0.357503,0.00001497934,0.6419128,0.00006585938,0.0000926787,0.0002656985,0.0000232671,0.00001226667,0.0001095503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9147586,"threshold_uncertainty_score":0.8931515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2909111255384714,"score_gpt":0.5436972920467246,"score_spread":0.2527861665082531,"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."}}