{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01127396,0.001212483,0.00257301,0.001607066,0.001577319,0.006032078,0.003317623,0.002678334,0.005112143],"category_scores_gemma":[0.07292976,0.0008485423,0.001650954,0.002405975,0.004345849,0.01536249,0.005424172,0.006212486,0.0007092968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004993861,"about_ca_system_score_gemma":0.003160933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006021409,"about_ca_topic_score_gemma":0.00400761,"domain_scores_codex":[0.9883975,0.005581477,0.0006563245,0.002323095,0.002280027,0.0007615389],"domain_scores_gemma":[0.8579969,0.1301583,0.002385185,0.006226904,0.002226726,0.001005942],"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":[0.001591681,0.0004174496,0.008738392,0.0007377283,0.000261883,0.0002791276,0.0008624666,0.3952203,0.001980408,0.4237373,0.01407138,0.1521018],"study_design_scores_gemma":[0.00006988526,0.00006429903,0.0007219053,0.00004264031,0.00003105736,0.00009900979,0.00009827948,0.6256481,0.0007396044,0.3711866,0.001270803,0.00002772798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1219394,0.002252465,0.8417401,0.01677108,0.0001987795,0.0003300197,0.00197577,0.001237288,0.01355509],"genre_scores_gemma":[0.7774211,0.002157341,0.2051524,0.002560393,0.0008996569,0.0007539605,0.003523564,0.0005026523,0.007028874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01127396,"threshold_uncertainty_score":0.05962312,"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."}}