{"id":"W4409364361","doi":"10.1609/aaai.v39i16.33887","title":"Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Measurement and Metrology Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Computer science; Semi-supervised learning; Artificial intelligence; Machine learning; Natural language processing","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":[0.006837943,0.002350556,0.002393608,0.001322885,0.001050659,0.002309139,0.003918092,0.002949058,0.003279649],"category_scores_gemma":[0.01428878,0.001237426,0.00163186,0.001355522,0.002979578,0.003447778,0.003902676,0.004392305,0.001633515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002248789,"about_ca_system_score_gemma":0.002859434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003411571,"about_ca_topic_score_gemma":0.005043959,"domain_scores_codex":[0.9947496,0.002573719,0.0002295576,0.001135533,0.001065196,0.0002463034],"domain_scores_gemma":[0.9909946,0.00526123,0.0007244264,0.001320494,0.001395932,0.00030329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002037118,0.0001743011,0.001086167,0.0002933097,0.0001244277,0.0000894011,0.0001700568,0.8571432,0.004118145,0.02232837,0.005068461,0.1092005],"study_design_scores_gemma":[0.000006815354,0.00002010453,0.00004387783,0.00000698511,0.000003038982,0.000009219599,0.000005544495,0.9921916,0.0005466846,0.006857043,0.0003033582,0.000005695348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002827109,0.0001077978,0.9957371,0.0001232856,0.00001681959,0.00004146267,0.00004722549,0.0006600024,0.0004392096],"genre_scores_gemma":[0.2218431,0.0002201024,0.7720673,0.0006235827,0.0001129946,0.0007195723,0.0009493048,0.0007933282,0.002670629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006837943,"threshold_uncertainty_score":0.03616297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07135756392470662,"score_gpt":0.2866357382010716,"score_spread":0.215278174276365,"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."}}