{"id":"W3194517965","doi":"10.1145/3479538","title":"Curiosity Notebook: The Design of a Research Platform for Learning by Teaching","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"AI in Service Interactions","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University of Edmonton; University of Waterloo","funders":"","keywords":"Curiosity; TUTOR; Computer science; Field (mathematics); Set (abstract data type); Mathematics education; Experiential learning; Human–computer interaction; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001866242,0.0001818062,0.0002373804,0.0001758442,0.0009652243,0.0003447831,0.00350732,0.00008958558,0.00001157045],"category_scores_gemma":[0.001299858,0.0001270192,0.000200494,0.000365867,0.00009387907,0.001141261,0.001993223,0.001242133,0.000009166599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001884154,"about_ca_system_score_gemma":0.00005275128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006743809,"about_ca_topic_score_gemma":0.000004335099,"domain_scores_codex":[0.9979517,0.0001039994,0.0004893002,0.0004819617,0.0006405049,0.0003325666],"domain_scores_gemma":[0.9953936,0.002055672,0.0005402199,0.0007693563,0.001196628,0.00004448475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003244858,0.001151844,0.000768651,0.0005746677,0.0003847603,0.000001831119,0.02643911,0.00415572,0.6455887,0.1372308,0.1288723,0.05450715],"study_design_scores_gemma":[0.0006847225,0.0009918739,0.0005574846,0.001167356,0.00004321773,0.00009567457,0.001841218,0.2013722,0.714236,0.05848706,0.02017563,0.0003475496],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5191858,0.00006072087,0.4573851,0.01509205,0.002428384,0.001618493,0.000006356366,0.0002650119,0.00395816],"genre_scores_gemma":[0.9281492,0.00000516363,0.07030682,0.0003823243,0.0002976557,0.00008092014,0.00000223318,0.00002534451,0.0007503993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4089634,"threshold_uncertainty_score":0.7423822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1637318166799974,"score_gpt":0.4101923123075898,"score_spread":0.2464604956275924,"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."}}