{"id":"W4409346487","doi":"10.1609/aaai.v39i2.32174","title":"Can Generative Models Improve Self-Supervised Representation Learning?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Vector Institute","funders":"","keywords":"Generative grammar; Computer science; Representation (politics); Generative model; Artificial intelligence; Machine learning","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":[0.0003861873,0.0002051523,0.0002491976,0.0001562065,0.0002655822,0.0003002201,0.001711654,0.00009518607,0.00001333889],"category_scores_gemma":[0.0002844273,0.0001647142,0.0001085921,0.0007362415,0.0001045317,0.0004901792,0.0004923049,0.0003677408,0.00001308226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008332408,"about_ca_system_score_gemma":0.0001998341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001370513,"about_ca_topic_score_gemma":0.00001565875,"domain_scores_codex":[0.9981065,0.00003456981,0.0005166547,0.0006338725,0.0004058904,0.0003024694],"domain_scores_gemma":[0.9984378,0.00008231228,0.0002675908,0.0003650022,0.0007863492,0.00006099501],"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":[0.00001642065,0.00006327277,0.0001172484,0.00002524424,0.00002018775,2.102471e-7,0.003105192,0.002988735,0.03447104,0.8988817,0.00004918126,0.06026156],"study_design_scores_gemma":[0.00001765798,0.00003947068,0.00001090098,0.00005034679,0.000006875533,3.877742e-7,0.0003707366,0.4952064,0.2532221,0.2509803,0.0000116255,0.0000831588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1715661,0.0000360819,0.7689831,0.01602894,0.00101108,0.0009276306,0.000003321476,0.0003704531,0.04107329],"genre_scores_gemma":[0.9786669,0.00003063211,0.01998192,0.0003943122,0.00005173091,0.00004574468,4.115751e-7,0.000008112122,0.0008202345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8071008,"threshold_uncertainty_score":0.6716849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07205294050913724,"score_gpt":0.3040885528802165,"score_spread":0.2320356123710792,"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."}}