{"id":"W4362714374","doi":"10.5642/jhummath.azev3747","title":"Human-Machine Collaboration in the Teaching of Proof","year":2023,"lang":"en","type":"article","venue":"Journal of Humanistic Mathematics","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Mathematical proof; Mathematics education; Autonomy; Mathematical logic; Instant; Computer science; Proof assistant; Natural (archaeology); Calculus (dental); Pedagogy; Mathematics; Programming language; 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":[],"consensus_categories":[],"category_scores_codex":[0.00274546,0.00008108438,0.0002379573,0.0001773727,0.0001151913,0.0001294958,0.0007398476,0.00003346076,0.000005083079],"category_scores_gemma":[0.0003222878,0.00004860343,0.00005849734,0.0003418661,0.00003009698,0.0001623763,0.00005999271,0.0002038158,0.000007473799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000269524,"about_ca_system_score_gemma":0.00005411561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006200497,"about_ca_topic_score_gemma":0.00002324988,"domain_scores_codex":[0.9985456,0.0001300158,0.0006704399,0.00007246959,0.0004552448,0.0001262149],"domain_scores_gemma":[0.9986618,0.0002286999,0.0006841363,0.0002656604,0.0001367028,0.00002298588],"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":[8.760576e-7,0.0001676604,0.0001107749,0.0001921735,0.00001398841,0.00004592447,0.01696108,0.00009354711,0.0002712039,0.9803011,0.001348402,0.000493289],"study_design_scores_gemma":[0.0008122534,0.0008459918,0.0007815062,0.0001423168,0.00005026645,0.0002668076,0.006883864,0.03491491,0.000290161,0.9500246,0.004767698,0.0002196201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05820847,0.0003515403,0.9169434,0.001424175,0.0008718494,0.0007978107,0.000001941966,0.00008125355,0.02131956],"genre_scores_gemma":[0.9924721,0.000002338144,0.007227076,0.00002460148,0.00008799347,0.000003417533,6.698937e-7,0.000005753826,0.0001760708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9342636,"threshold_uncertainty_score":0.198199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03897228720025611,"score_gpt":0.3218932369040875,"score_spread":0.2829209497038314,"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."}}