{"id":"W6929088210","doi":"10.48448/1dzq-x272","title":"Can Generative Models Improve Self-Supervised Representation Learning?","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Generative grammar; Leverage (statistics); Representation (politics); Generative model; Semantics (computer science); Workflow; Set (abstract data type)","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":[0.0001250649,0.0001915595,0.0001479748,0.0001852127,0.0001623581,0.00006644501,0.0002729868,0.0002433303,0.0001191167],"category_scores_gemma":[0.00005593264,0.0001749589,0.00005134373,0.000257528,0.0001884399,0.000006261505,0.0001529424,0.0001733578,0.00001147378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004026496,"about_ca_system_score_gemma":0.0004833532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003082272,"about_ca_topic_score_gemma":0.0002506837,"domain_scores_codex":[0.9987127,0.0000415824,0.0001401986,0.0006420513,0.0002331221,0.0002303549],"domain_scores_gemma":[0.9993007,0.000004384269,0.0001140642,0.0003743008,0.0001368337,0.00006967781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006757676,0.0001171669,0.0002351751,0.00008733622,0.0002811688,0.000007096376,0.0004029919,0.003004812,0.6629717,0.008095548,0.2595605,0.06516897],"study_design_scores_gemma":[0.001942152,0.001128967,0.00009520924,0.0001031272,0.000243499,0.00001733905,0.0007977728,0.1666424,0.1191588,0.005586397,0.7026495,0.001634878],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.002688814,0.0006248138,0.03658079,0.0006733449,0.00218425,0.0008144608,0.0001025432,0.0002768222,0.9560542],"genre_scores_gemma":[0.09739279,0.0006066432,0.03384199,0.001394157,0.001980089,0.00003378831,0.0008722938,0.0002591602,0.8636191],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5438129,"threshold_uncertainty_score":0.7134616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009413626408859883,"score_gpt":0.2584394374794763,"score_spread":0.2490258110706164,"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."}}