{"id":"W4393147232","doi":"10.1609/aaai.v38i13.29404","title":"Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Scaling; Artificial intelligence; Computer science; Machine learning; Semi-supervised learning; Mathematics","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":[0.001008161,0.0002401875,0.0002332612,0.0001604724,0.0002871265,0.0008319628,0.003209375,0.000082087,0.00006952405],"category_scores_gemma":[0.0007289696,0.0001601406,0.000056192,0.001080279,0.0002453375,0.000883963,0.0007184174,0.0006576537,0.0001291856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000335615,"about_ca_system_score_gemma":0.0002273177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000545508,"about_ca_topic_score_gemma":0.000008277389,"domain_scores_codex":[0.9977596,0.00003993314,0.0004594623,0.0008606156,0.0005549655,0.0003253998],"domain_scores_gemma":[0.9984221,0.0002474794,0.0002077901,0.0006786914,0.0003514565,0.00009245171],"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":[0.00004469465,0.00003716331,0.0002537219,0.0001048806,0.00003097426,0.00000143468,0.00143848,0.0001980592,0.02088023,0.6636298,0.0001994058,0.3131812],"study_design_scores_gemma":[0.00003693779,0.000132457,0.00006630883,0.0006702936,0.00002651905,0.0000150521,0.0008144914,0.9252207,0.05687678,0.01430866,0.001572303,0.0002594757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.159941,0.0003468825,0.7652981,0.02771968,0.001960814,0.001217433,0.00004775869,0.001723095,0.04174531],"genre_scores_gemma":[0.9934289,0.00004700492,0.005589521,0.00008522287,0.00008144856,0.00001258239,0.00001245298,0.00001843997,0.000724406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9250227,"threshold_uncertainty_score":0.8022637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1052760270466039,"score_gpt":0.3173109003364958,"score_spread":0.2120348732898919,"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."}}