{"id":"W2949833607","doi":"10.48550/arxiv.1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Representation (politics); Computer science; Artificial intelligence; Learning to learn; Feature learning; Active learning (machine learning); Data science; Machine learning; Mathematics education; Psychology; Political science","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":[0.04311952,0.003353053,0.003817817,0.004926904,0.005567324,0.01359234,0.004958752,0.005165655,0.01290248],"category_scores_gemma":[0.04563088,0.0008180442,0.002760589,0.007027061,0.003697047,0.01082109,0.0167286,0.01016227,0.00813999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006799866,"about_ca_system_score_gemma":0.009620399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01694451,"about_ca_topic_score_gemma":0.02428427,"domain_scores_codex":[0.9747791,0.006102595,0.001261809,0.002634625,0.01109737,0.00412448],"domain_scores_gemma":[0.9414866,0.01596592,0.001265493,0.004857842,0.02129525,0.01512893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002458878,0.0003028709,0.001258136,0.0005852444,0.00008235157,0.0001171953,0.0003852171,0.001883238,0.0008024549,0.01332587,0.8733804,0.1076312],"study_design_scores_gemma":[0.0001807374,0.0002725308,0.006631083,0.0005565476,0.00007822686,0.0004337794,0.001807283,0.01172059,0.003921942,0.04826097,0.9259396,0.0001967062],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.09354947,0.1513638,0.1623434,0.3346093,0.06762651,0.002245442,0.03877367,0.009459716,0.1400288],"genre_scores_gemma":[0.3538744,0.04825884,0.1576356,0.0342258,0.03868993,0.003550609,0.1886837,0.007864237,0.1672168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04311952,"threshold_uncertainty_score":0.2280405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1648509459164146,"score_gpt":0.2514998793910733,"score_spread":0.08664893347465866,"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."}}