{"id":"W4392445341","doi":"10.1145/3636555.3636876","title":"Does Difficulty even Matter? Investigating Difficulty Adjustment and Practice Behavior in an Open-Ended Learning Task","year":2024,"lang":"en","type":"article","venue":"","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Leibniz-Gemeinschaft; Deutsche Forschungsgemeinschaft","keywords":"Task (project management); Computer science; Intervention (counseling); Space (punctuation); Cognitive psychology; Psychology; Mathematics education; Applied 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":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006176767,0.000448506,0.000561196,0.0006528265,0.0002357574,0.001920834,0.0005274362,0.0006957544,0.002297672],"category_scores_gemma":[0.09242781,0.0002103314,0.0004381297,0.000415253,0.0007107503,0.001449984,0.0008453662,0.000831701,0.0004374037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002948458,"about_ca_system_score_gemma":0.0003141937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004697935,"about_ca_topic_score_gemma":0.0006936319,"domain_scores_codex":[0.9944196,0.002222141,0.0006138277,0.0009392858,0.001516459,0.000288698],"domain_scores_gemma":[0.9194291,0.0601106,0.01251012,0.002935444,0.003107392,0.001907281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002656469,0.003457695,0.7394369,0.0009888475,0.0005814179,0.0003471875,0.03401031,0.00128735,0.0424246,0.0008083536,0.0009626638,0.1730382],"study_design_scores_gemma":[0.00008715778,0.003703478,0.9765139,0.0001779987,0.0001579246,0.000311408,0.006619943,0.003409195,0.005532369,0.00115224,0.002237231,0.00009717016],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943014,0.0001198895,0.003891461,0.00006821784,0.00001616969,0.0001173846,0.0000457091,0.00002964247,0.00141015],"genre_scores_gemma":[0.9962502,0.00009824541,0.002566289,0.000051561,0.00001102731,0.0001628897,0.00009086137,0.00002596215,0.0007428846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006176767,"threshold_uncertainty_score":0.03266627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07063212001494298,"score_gpt":0.433313213453595,"score_spread":0.3626810934386521,"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."}}