{"id":"W7117481005","doi":"10.2139/ssrn.5978094","title":"A Comprehensive Survey on Large Language Models: From Pre-training to Autonomous Agents","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Canada West","funders":"","keywords":"Interoperability; Transformative learning; Architecture; Key (lock); Natural language understanding; Inference; Open research","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":[0.004449454,0.001700697,0.002782897,0.001911196,0.0006973682,0.003076965,0.003148468,0.002168187,0.004713512],"category_scores_gemma":[0.02244522,0.001242829,0.00153373,0.002753285,0.0009159964,0.006792081,0.00250486,0.003457488,0.00374681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001387635,"about_ca_system_score_gemma":0.003403968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005977315,"about_ca_topic_score_gemma":0.007265405,"domain_scores_codex":[0.9970875,0.001471034,0.0002245891,0.0006261496,0.0004587205,0.0001321158],"domain_scores_gemma":[0.9805477,0.01623436,0.0002820135,0.001691365,0.0009204994,0.0003240159],"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":[0.0002257114,0.000354073,0.002363205,0.002032205,0.0002907474,0.00009492194,0.0003229444,0.09038093,0.001663199,0.02870456,0.03563649,0.837931],"study_design_scores_gemma":[0.00005516462,0.0002525858,0.00130644,0.0006017382,0.0001960753,0.0002202374,0.0002333507,0.7974631,0.002793094,0.140926,0.05588569,0.00006658282],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.0107938,0.07755289,0.8935498,0.005352769,0.0006036457,0.0001581944,0.001514424,0.004403897,0.006070536],"genre_scores_gemma":[0.271066,0.1181933,0.575168,0.003436334,0.003802643,0.001022731,0.01155311,0.002573488,0.01318443],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.005977315,"threshold_uncertainty_score":0.02353126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05460445667758154,"score_gpt":0.3138997307637531,"score_spread":0.2592952740861716,"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."}}