{"id":"W3114166581","doi":"10.1613/jair.1.12013","title":"On the Complexity of Learning a Class Ratio from Unlabeled Data","year":2020,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Science Foundation","keywords":"Learnability; VC dimension; Class (philosophy); Sample complexity; Axiom; Variety (cybernetics); Computer science; Artificial intelligence; Dimension (graph theory); Set (abstract data type); Machine learning; Concept class; Theoretical computer science; Mathematics; Combinatorics","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":[0.004485387,0.00009873666,0.0002535661,0.0001399177,0.0002982193,0.0002639735,0.003466774,0.00004758667,0.0001968748],"category_scores_gemma":[0.005338718,0.00006390448,0.00007678253,0.0009483756,0.0004123788,0.000320892,0.0007709243,0.001834257,0.0001127292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000288227,"about_ca_system_score_gemma":0.000271993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001552664,"about_ca_topic_score_gemma":0.00001467906,"domain_scores_codex":[0.9962269,0.001225093,0.0006399709,0.0002822291,0.001334241,0.0002915747],"domain_scores_gemma":[0.9960217,0.002248102,0.0003388592,0.0005969682,0.0006249752,0.000169368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003614617,0.0003547665,0.000290673,0.00002800482,0.0001368432,0.0001121098,0.006752402,0.02007114,0.02677332,0.5856059,0.004449014,0.3550644],"study_design_scores_gemma":[0.00003285562,0.0007199048,0.00006662431,0.00005683766,0.000003973956,0.000004360308,0.000945403,0.913615,0.02284399,0.06013723,0.001503493,0.00007030754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06199339,0.0001266275,0.8818092,0.05521692,0.0002195813,0.0001341703,0.000007858253,0.00002168116,0.0004705655],"genre_scores_gemma":[0.9893782,0.00004106811,0.009935169,0.0001734871,0.0004353989,7.488695e-7,0.000002556784,0.000007589659,0.00002584727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9273847,"threshold_uncertainty_score":0.7969034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.485213038720513,"score_gpt":0.4485199828397629,"score_spread":0.03669305588075011,"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."}}