{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1073614,0.0007197212,0.001086995,0.006931193,0.003737605,0.01274689,0.003304143,0.002294022,0.00200836],"category_scores_gemma":[0.1036191,0.0007234466,0.0005128068,0.002791048,0.01082061,0.01216741,0.007138412,0.00418921,0.000339713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009592427,"about_ca_system_score_gemma":0.02370873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006548916,"about_ca_topic_score_gemma":0.01556412,"domain_scores_codex":[0.9160234,0.0671379,0.004543215,0.002431045,0.008926941,0.0009375088],"domain_scores_gemma":[0.8554647,0.1100991,0.004806357,0.005702162,0.02198601,0.001941617],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001286989,0.0009073848,0.0145846,0.002682714,0.00007620965,0.0003962311,0.1520956,0.004028019,0.002430608,0.3939084,0.003738533,0.4250231],"study_design_scores_gemma":[0.0003795832,0.001780813,0.01284397,0.01720958,0.0004310572,0.000780649,0.2467671,0.04039263,0.01638038,0.4509398,0.2117002,0.0003942948],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2055382,0.01099493,0.6865259,0.02109332,0.0004934644,0.004403373,0.0001469057,0.0006140529,0.07018997],"genre_scores_gemma":[0.6051421,0.001270094,0.3894216,0.0005052359,0.00002922616,0.001528735,0.00004223976,0.00005522569,0.002005453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8926386,"threshold_uncertainty_score":0.5677879,"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."}}