{"id":"W2316658219","doi":"10.1119/perc.2013.pr.047","title":"Development of a General Undergraduate Estimation Skills Survey (GUESS)","year":2014,"lang":"en","type":"article","venue":"","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Test (biology); Class (philosophy); Set (abstract data type); Computer science; Mathematics education; Estimation; Baseline (sea); Machine learning; Multiple choice; Artificial intelligence; Statistics; Psychology; Mathematics; Engineering; Significant difference","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":[0.001436728,0.00007124574,0.0001505009,0.0000511217,0.00003663856,0.00001024128,0.00007616587,0.00003144362,0.00008797024],"category_scores_gemma":[0.00491417,0.00005770078,0.00001664768,0.00007954617,0.00002547756,0.00002230815,0.00002362568,0.0000307582,0.00003155057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002107491,"about_ca_system_score_gemma":0.00008270828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002517394,"about_ca_topic_score_gemma":0.000109468,"domain_scores_codex":[0.9991614,0.0002217831,0.0002892682,0.00009811617,0.0001313698,0.00009805567],"domain_scores_gemma":[0.997863,0.00171461,0.0001221719,0.0001514802,0.0001154869,0.00003322781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009211952,0.0002373893,0.001758936,0.0001241775,0.00004241903,9.249469e-8,0.00169169,0.00004523588,0.0009300733,0.8843436,0.02941019,0.08140703],"study_design_scores_gemma":[0.0004889478,0.00003175417,0.10305,0.00003578251,0.00002410055,0.000002229055,0.0001641188,0.008904879,0.05200393,0.8314109,0.00360034,0.0002830001],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1163602,0.000001747643,0.8782192,0.00006980875,0.0002632666,0.00007204875,0.000005245743,0.00004463091,0.004963795],"genre_scores_gemma":[0.1363489,0.00000189246,0.8592038,0.00004105731,0.00001301883,0.000007458098,0.00002961062,0.000007559306,0.00434667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1012911,"threshold_uncertainty_score":0.5883075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.200871181720234,"score_gpt":0.4406332209790296,"score_spread":0.2397620392587956,"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."}}