{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004707704,0.001123301,0.001075227,0.0006361706,0.0004636896,0.001280889,0.002137444,0.002035458,0.001312554],"category_scores_gemma":[0.0163775,0.0005019497,0.0004359349,0.0005076148,0.002177129,0.00344795,0.00292434,0.002595363,0.0003811967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001218703,"about_ca_system_score_gemma":0.001036531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00176219,"about_ca_topic_score_gemma":0.002155066,"domain_scores_codex":[0.9981019,0.0009090255,0.00008266792,0.0004190078,0.000365375,0.0001219768],"domain_scores_gemma":[0.9906911,0.006962266,0.000478192,0.001004167,0.0005488541,0.0003154372],"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":[0.0003085391,0.0002959693,0.003264277,0.0002998497,0.0001252812,0.00009851079,0.0002401993,0.7879677,0.006837541,0.0385249,0.002613791,0.1594234],"study_design_scores_gemma":[0.00001583797,0.00008679698,0.0001223973,0.000008635891,0.000005168494,0.00002046131,0.00001211577,0.9862054,0.001468567,0.01180956,0.0002386199,0.000006461708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08574997,0.0009735861,0.9077847,0.0009703455,0.00005008025,0.0001248009,0.00009739273,0.0008072113,0.003441898],"genre_scores_gemma":[0.8473903,0.0003573145,0.148362,0.0005823347,0.00010956,0.0001992671,0.000254409,0.0002102481,0.002534546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004707704,"threshold_uncertainty_score":0.02489704,"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."}}