{"id":"W4416075695","doi":"10.31224/5781","title":"Retrieval-Augmented Generation","year":2025,"lang":"","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Natural language generation; Key (lock); Generative grammar; Natural language; Context (archaeology); Language model; Information extraction; Architecture","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009102748,0.0005013553,0.0005046741,0.0003232905,0.0002789926,0.0008314134,0.002241938,0.0005722983,0.0006255586],"category_scores_gemma":[0.0001417423,0.0005240259,0.0002627575,0.0005826122,0.00004347978,0.0003380105,0.004495954,0.0008173663,0.000207934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003376541,"about_ca_system_score_gemma":0.00104951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001855525,"about_ca_topic_score_gemma":0.00002621016,"domain_scores_codex":[0.9954393,0.0002499697,0.001059191,0.001982945,0.0007471862,0.0005214337],"domain_scores_gemma":[0.9962201,0.0000798292,0.0003062471,0.002753247,0.0004744588,0.0001660857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003974613,0.0003447557,0.0001988091,0.0005938502,0.0003941913,0.00003400675,0.002508037,0.1640671,0.007303352,0.3920515,0.01509055,0.417374],"study_design_scores_gemma":[0.0002990168,0.00002781827,0.000038748,0.000185629,0.00003630069,0.000003169426,0.00001155137,0.9760423,0.01168607,0.003099292,0.008116304,0.0004537845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003002229,0.0004620982,0.9368744,0.003959111,0.009181683,0.0007257937,0.000008745439,0.0002804484,0.04550552],"genre_scores_gemma":[0.2593449,0.001095488,0.5109475,0.003933626,0.002374915,0.0000491548,0.00008706818,0.00002709688,0.2221402],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8119752,"threshold_uncertainty_score":0.9997211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06732035046122521,"score_gpt":0.2972475834883907,"score_spread":0.2299272330271655,"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."}}