{"id":"W4229076201","doi":"10.24963/ijcai.2022/538","title":"Learning Curricula for Humans: An Empirical Study with Puzzles from The Witness","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Curriculum; Computer science; Witness; Set (abstract data type); Class (philosophy); Process (computing); Artificial intelligence; Domain (mathematical analysis); Tree (set theory); Machine learning; Human–computer interaction; Programming language; Mathematics; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007960914,0.0008555313,0.0008446291,0.001375038,0.001022915,0.001582887,0.00162206,0.001666246,0.00631102],"category_scores_gemma":[0.06739745,0.000505745,0.0005539965,0.0008774641,0.001575583,0.003717816,0.002151537,0.002369438,0.001977097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000750516,"about_ca_system_score_gemma":0.0005753614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001892465,"about_ca_topic_score_gemma":0.003573836,"domain_scores_codex":[0.9949591,0.002993484,0.0004325745,0.0006511316,0.0007337364,0.0002299772],"domain_scores_gemma":[0.9303154,0.05479906,0.002766144,0.006531882,0.003101798,0.002485739],"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":[0.005167142,0.02852463,0.2351791,0.00370976,0.0005697123,0.002119398,0.06045556,0.02923119,0.01201185,0.009760953,0.06460122,0.5486695],"study_design_scores_gemma":[0.00289126,0.04372328,0.4154945,0.001301475,0.0004026532,0.005322373,0.05693009,0.1831465,0.02969136,0.02279237,0.2376951,0.0006089974],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875425,0.0003395824,0.00615883,0.0003189942,0.00003408912,0.0004016269,0.000562362,0.0003423639,0.004299614],"genre_scores_gemma":[0.9792575,0.0003353677,0.01262487,0.0002541049,0.00002873468,0.000431237,0.002143525,0.0001179769,0.004806704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007960914,"threshold_uncertainty_score":0.04210186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09833545549548467,"score_gpt":0.3364742101218567,"score_spread":0.238138754626372,"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."}}