{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003527422,0.0006091221,0.0006822064,0.003926777,0.000405968,0.002809684,0.0008580057,0.0007376331,0.001640163],"category_scores_gemma":[0.02932326,0.0003207129,0.0003300413,0.003092174,0.0002618081,0.003349163,0.001963741,0.001468869,0.001792399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003625472,"about_ca_system_score_gemma":0.001200897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004365137,"about_ca_topic_score_gemma":0.00803372,"domain_scores_codex":[0.9972126,0.0007548828,0.0002931473,0.0005190254,0.001037751,0.0001826091],"domain_scores_gemma":[0.9760215,0.009357566,0.002706656,0.006105077,0.004547873,0.00126123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007290025,0.001018793,0.373339,0.0002236364,0.0002326406,0.0002189088,0.002566843,0.007781917,0.007917811,0.005212461,0.01164629,0.5891127],"study_design_scores_gemma":[0.00007942423,0.001324615,0.3222558,0.0005262588,0.000225418,0.0009164071,0.004283794,0.5097409,0.04499605,0.05938587,0.05590222,0.0003632263],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4623731,0.0007783858,0.4929667,0.001536856,0.0004573262,0.000540405,0.01712198,0.01373145,0.01049372],"genre_scores_gemma":[0.8973771,0.0002844226,0.09049864,0.0001516978,0.0001000537,0.0001845,0.007164239,0.0004355873,0.003803772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004365137,"threshold_uncertainty_score":0.018655,"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."}}