{"id":"W7117339936","doi":"","title":"How to Do STEM Outreach Evaluation -- Recommendations Based on a Review of Self Evaluation Tools in Canadian STEM Outreach Programs","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Career Development and Diversity","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Outreach; Grassroots; Toolbox; Program evaluation; Accreditation; Equity (law)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01251402,0.0003421514,0.000577688,0.0007757455,0.0005825608,0.000301522,0.0005767984,0.0002531906,0.0004655928],"category_scores_gemma":[0.0007391552,0.0003796932,0.0002088164,0.003338121,0.00007664273,0.0005969785,0.0001012679,0.0002756902,0.00008326422],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.005330477,"about_ca_system_score_gemma":0.007297738,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06716286,"about_ca_topic_score_gemma":0.4410049,"domain_scores_codex":[0.9943265,0.001657841,0.0007783677,0.0008103728,0.001698606,0.0007282606],"domain_scores_gemma":[0.9965507,0.0002521596,0.0003726212,0.0005887725,0.001811121,0.0004246257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001814065,0.0002479028,0.6539182,0.0005108858,0.00005846188,0.000001399073,0.006151367,0.00002091766,0.000002386149,0.0002861374,0.004251373,0.3345328],"study_design_scores_gemma":[0.002888724,0.0003318741,0.8410032,0.01739877,0.001203562,2.404607e-7,0.02057373,0.003557814,0.0001082522,0.00009293693,0.11193,0.0009108167],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8434412,0.004072031,0.00005235281,0.09963331,0.00208125,0.01279124,0.0001246292,0.0000852945,0.03771862],"genre_scores_gemma":[0.9949327,0.0009009613,0.0001772622,0.001680687,0.00006423571,0.0004616765,0.0003380212,0.00001387169,0.001430659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3738421,"threshold_uncertainty_score":0.9998655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1644875471048291,"score_gpt":0.3603523388773321,"score_spread":0.195864791772503,"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."}}