{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001563222,0.0001377639,0.000249115,0.0001275936,0.0004475282,0.00005753816,0.0003839988,0.00008968342,0.0002017767],"category_scores_gemma":[0.001576297,0.00007960712,0.00005189488,0.001274182,0.002523945,0.0001649639,0.0001952932,0.0003915277,0.00002005351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006404646,"about_ca_system_score_gemma":0.0004092697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001254056,"about_ca_topic_score_gemma":0.00003227699,"domain_scores_codex":[0.9981754,0.00009160154,0.0004077371,0.0004047144,0.0004199093,0.0005006474],"domain_scores_gemma":[0.9982591,0.0008635111,0.00005564541,0.0002901153,0.0002986952,0.0002329459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001938595,0.00007458763,0.0003580608,0.00006251183,0.000009029615,0.000002107798,0.02059989,0.000003985101,0.0146472,0.9156325,0.00009416694,0.0483221],"study_design_scores_gemma":[0.00008944027,0.0002038783,0.003629691,0.0008020974,0.0001116778,0.00000361672,0.02199053,0.04835324,0.2561457,0.6684592,0.0000352147,0.000175675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9608716,0.004387047,0.002429852,0.02716384,0.001126938,0.0003800071,0.00001567643,0.00001287934,0.003612199],"genre_scores_gemma":[0.9967486,0.0001759986,0.0001955352,0.002394624,0.0002814181,0.000005795878,0.000001949575,0.000004063119,0.0001920367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2471733,"threshold_uncertainty_score":0.9299582,"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."}}