{"id":"W7144138757","doi":"10.59400/cai3914","title":"MDL-AE: Investigating the trade-off between compressive fidelity and discriminative utility in self-supervised learning","year":2025,"lang":"","type":"article","venue":"Computing and artificial intelligence.","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Discriminative model; Feature learning; Heuristics; Bridging (networking); Autoencoder; Fidelity; Generative grammar; Chunking (psychology); Classifier (UML); Encoder","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003319065,0.0005305977,0.0007237297,0.0002939235,0.002286995,0.001304916,0.000849991,0.0002353957,0.00001807195],"category_scores_gemma":[0.001234697,0.0004704611,0.0001260648,0.001474528,0.001164235,0.0004295976,0.001157335,0.001886725,0.000008557137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008407292,"about_ca_system_score_gemma":0.0002618068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003260715,"about_ca_topic_score_gemma":0.00007620007,"domain_scores_codex":[0.9940292,0.00188373,0.001510321,0.001308494,0.0004387379,0.0008295223],"domain_scores_gemma":[0.9951174,0.003497967,0.0004847081,0.0004685091,0.0001683345,0.0002631019],"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":[0.00001477212,0.00008983436,0.02223746,0.0001386829,0.00005744325,0.000008309879,0.06377424,0.004451469,0.00008252396,0.02481599,0.00002125408,0.884308],"study_design_scores_gemma":[0.0001319627,0.0001011787,0.05755142,0.0006991908,0.00005569807,0.000004158796,0.01943263,0.8981795,0.0007664957,0.02211788,0.0005456653,0.000414169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5400509,0.002542766,0.449981,0.004439264,0.0005936229,0.0006333875,0.000004668265,0.0001841057,0.001570345],"genre_scores_gemma":[0.9932529,0.0001893107,0.005787717,0.0004916715,0.0001922057,0.000008201328,0.000006691153,0.00001774761,0.00005357377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8937281,"threshold_uncertainty_score":0.9997747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06809786225321061,"score_gpt":0.3288031412653231,"score_spread":0.2607052790121124,"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."}}