{"id":"W4415926346","doi":"10.54254/2753-8818/2025.dl29003","title":"From GPT to LLaMA: Tracing the Growth of Large Language Models","year":2025,"lang":"","type":"article","venue":"Theoretical and Natural Science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"LEAPS; Language model; Scaling; Tracing; Key (lock); Natural language; Scaling law","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":[0.004945611,0.0009958019,0.0009492587,0.002276695,0.0006386492,0.003973141,0.001456888,0.001123149,0.003703014],"category_scores_gemma":[0.04955943,0.001014898,0.001119778,0.002209563,0.001818717,0.0110905,0.002401415,0.004784797,0.001548855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002252918,"about_ca_system_score_gemma":0.001784751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006133919,"about_ca_topic_score_gemma":0.005895178,"domain_scores_codex":[0.9982429,0.0007680909,0.0000886265,0.0003888601,0.0004303097,0.00008123964],"domain_scores_gemma":[0.9811968,0.01507182,0.0006010627,0.001631356,0.001142491,0.0003563254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000370244,0.0001074112,0.01625796,0.001619744,0.0003978306,0.0005601733,0.002095234,0.3152241,0.004550697,0.2829309,0.03637066,0.339515],"study_design_scores_gemma":[0.0000340669,0.000128863,0.00242055,0.0004205499,0.0000979506,0.0003620371,0.0003078574,0.6684368,0.003566801,0.2704498,0.05368365,0.00009109943],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.1615723,0.05632785,0.7100204,0.02645984,0.0008753448,0.0001913913,0.004415285,0.008467505,0.03167012],"genre_scores_gemma":[0.6657751,0.02908138,0.290202,0.002767003,0.0005490696,0.0003974941,0.004478041,0.002444535,0.004305326],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.006133919,"threshold_uncertainty_score":0.02615517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02585271452559845,"score_gpt":0.3912550438801011,"score_spread":0.3654023293545027,"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."}}