{"id":"W4317381171","doi":"10.3138/cjpe.74487","title":"New Insights for Tracking and Reporting Milestones","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Tracking (education); Reflection (computer programming); Process (computing); Metric (unit); Developmental Milestone; Key (lock); Critical reflection; Psychology; Computer science; Operations management; Pedagogy; Engineering; Computer security; Developmental psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01736877,0.00006892241,0.0001866544,0.0005065588,0.0005494458,0.0003062557,0.000215643,0.00002443933,0.001117283],"category_scores_gemma":[0.005482341,0.00005648795,0.00008680702,0.0004439417,0.00002491884,0.0004291929,0.00001382826,0.0001406291,0.000002224931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002410401,"about_ca_system_score_gemma":0.005292828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000294796,"about_ca_topic_score_gemma":0.005773356,"domain_scores_codex":[0.9965966,0.0002721108,0.001322131,0.0001563149,0.001489548,0.0001632443],"domain_scores_gemma":[0.9958066,0.000245248,0.002118258,0.0001381683,0.001359538,0.0003321622],"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":[0.0000108549,0.000008527662,0.01361586,0.000002127751,0.00001034381,0.000004146065,0.002236497,0.002793763,0.00005516301,0.0004692367,0.00385379,0.9769397],"study_design_scores_gemma":[0.00217033,0.001542125,0.1666889,0.00003928184,0.0001544444,0.0004220367,0.01023132,0.1060952,0.0002100434,0.07818985,0.6339875,0.000268963],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851238,0.001590662,0.006014438,0.003640134,0.00140103,0.001331997,0.000004348239,0.000007735525,0.0008859148],"genre_scores_gemma":[0.9890606,0.000003443615,0.01023413,0.000161692,0.0001870245,0.00007516749,0.000006886398,0.000006795574,0.00026431],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9766707,"threshold_uncertainty_score":0.9997959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6188240831545975,"score_gpt":0.573439920067952,"score_spread":0.0453841630866455,"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."}}