{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007366582,0.002032608,0.001999297,0.00137876,0.0008930499,0.001821557,0.004551933,0.002228853,0.001991596],"category_scores_gemma":[0.01978289,0.001009846,0.001406869,0.001016557,0.002321343,0.004550408,0.004596727,0.003311329,0.002036986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051983,"about_ca_system_score_gemma":0.001568974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001766518,"about_ca_topic_score_gemma":0.003334954,"domain_scores_codex":[0.9939604,0.002507184,0.0002257074,0.001496301,0.001562777,0.0002476768],"domain_scores_gemma":[0.9834772,0.008035016,0.001108946,0.00445574,0.002410289,0.0005128144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004598795,0.0006728616,0.004359249,0.0005234298,0.0003204585,0.0002388828,0.0005677196,0.42524,0.02548696,0.01084397,0.01076904,0.5205175],"study_design_scores_gemma":[0.00002610251,0.00008252767,0.0003536621,0.0000230022,0.00001463938,0.00006509005,0.00004083792,0.9754455,0.006197367,0.01620574,0.001521424,0.00002412831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02350242,0.0002740158,0.9711902,0.0002212292,0.00007161938,0.0001535305,0.0001573615,0.002994677,0.001434977],"genre_scores_gemma":[0.3126014,0.0002103542,0.6807243,0.0006499816,0.0001701556,0.0004887203,0.001703797,0.0007171387,0.002734096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007366582,"threshold_uncertainty_score":0.03895867,"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."}}