{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.001483483,0.00038483,0.0003816434,0.0001764381,0.001547519,0.0006668415,0.005575395,0.00006526295,0.0002091787],"category_scores_gemma":[0.0006977349,0.0002438329,0.0002044566,0.0007077974,0.0005255439,0.0007654819,0.001361479,0.0008753677,0.00002598398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001908097,"about_ca_system_score_gemma":0.0001568271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003452322,"about_ca_topic_score_gemma":0.0002883305,"domain_scores_codex":[0.9958683,0.0001262268,0.000930643,0.0009896646,0.001638973,0.0004462424],"domain_scores_gemma":[0.996663,0.0005761159,0.0008100715,0.0005490234,0.001295308,0.0001064504],"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":[0.0006760936,0.002108314,0.02891101,0.00001595813,0.0001888187,0.000005249344,0.02904603,0.01428005,0.002143863,0.8919258,0.0003779847,0.03032086],"study_design_scores_gemma":[0.000211476,0.005072319,0.007451442,0.0003348249,0.0001051217,0.00002966969,0.08201423,0.3786945,0.08045864,0.4419741,0.00256558,0.001088088],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8899853,0.00002740257,0.08644334,0.01821699,0.00159366,0.00197298,0.00004589801,0.0002416585,0.001472768],"genre_scores_gemma":[0.9962023,0.000008896382,0.002271725,0.0005111501,0.0002634494,0.0005238403,0.000006433155,0.000032373,0.0001798411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4499517,"threshold_uncertainty_score":0.9998049,"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."}}