{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002780885,0.000174526,0.0002040005,0.0001485102,0.000146294,0.00004484741,0.0003454047,0.00009294082,0.00002255894],"category_scores_gemma":[0.00026974,0.0001337729,0.00005436099,0.0003999838,0.00009946972,0.0001524681,0.0000369658,0.0002394507,0.000002143551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004801858,"about_ca_system_score_gemma":0.00003502658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002569304,"about_ca_topic_score_gemma":0.000003835095,"domain_scores_codex":[0.9990804,0.000005039302,0.0003007074,0.0002180057,0.0001579303,0.0002378816],"domain_scores_gemma":[0.9992113,0.00005855634,0.00009542025,0.00009600956,0.0005094633,0.00002929028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003854936,0.0000913782,0.0009835728,0.0003850615,0.0001030421,1.420777e-7,0.0005565927,0.3057669,0.4431963,0.161467,0.0001863867,0.08687816],"study_design_scores_gemma":[0.00004253455,0.0001087009,0.00001126534,0.0002917603,0.00002848658,3.503481e-7,0.0002704708,0.4178113,0.5731558,0.008078277,0.00008415785,0.0001168446],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08293705,0.00005628807,0.9060575,0.0004922902,0.0002287266,0.0007201175,0.000004467162,0.0003839712,0.009119578],"genre_scores_gemma":[0.9475683,0.00009265907,0.05184772,0.00006271179,0.00002871406,0.0001001369,0.000001647653,0.00002118015,0.0002769356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8646312,"threshold_uncertainty_score":0.5455099,"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."}}