{"id":"W7133020277","doi":"","title":"Towards the Renormalization of Transformer Language Models","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformer; Natural language; Abstraction; Cognition; Language model; Granularity; Function (biology); Knowledge base; Philosophy of language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001624631,0.0006914697,0.000923302,0.0009017642,0.0007423271,0.002234151,0.001825633,0.001275499,0.004958004],"category_scores_gemma":[0.009530287,0.0007463743,0.001632424,0.0003965595,0.001917679,0.003651683,0.003134761,0.003765398,0.001705219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001482761,"about_ca_system_score_gemma":0.001193171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002104823,"about_ca_topic_score_gemma":0.002474221,"domain_scores_codex":[0.9991753,0.0003573511,0.00003725037,0.0001711231,0.0001921147,0.00006679404],"domain_scores_gemma":[0.997335,0.001574131,0.0001602647,0.0005762657,0.0002526389,0.0001016226],"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":[0.00004649673,0.00002663495,0.0004157267,0.0001009533,0.00003521059,0.0001506675,0.0003668877,0.06672814,0.003921499,0.8833011,0.003142982,0.04176366],"study_design_scores_gemma":[0.000009040645,0.00001295094,0.00006270748,0.00001796055,0.000008011591,0.00003853046,0.00003199104,0.4465356,0.0006988941,0.5482365,0.004336674,0.00001109345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01235231,0.0002982367,0.9758957,0.000959116,0.00008332944,0.00003475915,0.00007126049,0.0005445906,0.009760602],"genre_scores_gemma":[0.4751546,0.000988237,0.5027242,0.001253257,0.0003979877,0.0002971085,0.0004370279,0.0009648465,0.01778279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004958004,"threshold_uncertainty_score":0.01658618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03666717723620515,"score_gpt":0.3276809395045835,"score_spread":0.2910137622683784,"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."}}