{"id":"W4386366486","doi":"10.3102/ip.23.2008230","title":"Student Self-Assessment Profiles: Leveraging Trace Data to Unpack the Black Box of Self-Assessment","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Data Processing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Self-assessment; TRACE (psycholinguistics); Black box; Computer science; Data science; Artificial intelligence; Psychology","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":[0.0008732537,0.0002955405,0.0003114698,0.0001602487,0.0001134394,0.0001113632,0.00167162,0.00006630868,0.00004134968],"category_scores_gemma":[0.00001057575,0.0002256137,0.00003988474,0.0008192846,0.00003011981,0.0005209318,0.001107806,0.000311366,0.00006166173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004011034,"about_ca_system_score_gemma":0.0001489099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277303,"about_ca_topic_score_gemma":0.000009809735,"domain_scores_codex":[0.9978611,0.00005189461,0.0004963062,0.000505945,0.000614862,0.0004699294],"domain_scores_gemma":[0.9977202,0.0001557466,0.0000803709,0.001853748,0.00008366365,0.0001062707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003194547,0.001962922,0.03828199,0.003978243,0.002255404,0.0001364916,0.02344301,0.1617168,0.07295623,0.01944947,0.623063,0.05272449],"study_design_scores_gemma":[0.001454711,0.0003754105,0.1292514,0.0006496626,0.0002884185,0.00001850382,0.01297721,0.7044241,0.04265538,0.001693264,0.1041404,0.002071483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2949068,0.0001728442,0.6751907,0.00218851,0.0005176938,0.002820556,0.0003453901,0.01488692,0.008970601],"genre_scores_gemma":[0.6775464,0.0002755205,0.3216093,0.00009524617,0.00006214011,0.0001325686,0.0001255293,0.00007722409,0.00007606562],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5427074,"threshold_uncertainty_score":0.9200259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03803778660203025,"score_gpt":0.3542534167229908,"score_spread":0.3162156301209605,"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."}}