{"id":"W4417109773","doi":"10.1007/s42454-025-00085-9","title":"Securing local LLMs for academic research: a human-system integration analysis and evolution of TAUCHI-GPT","year":2025,"lang":"en","type":"article","venue":"Human-Intelligent Systems Integration","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"McGill University; Google","keywords":"Sociotechnical system; Workflow; Interpretability; Software deployment; Work (physics); Reflection (computer programming); Risk management","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002953009,0.0002815158,0.0007374615,0.002213847,0.0006387812,0.00008572519,0.0001863069,0.0004666035,0.00002533233],"category_scores_gemma":[0.000603314,0.0002286258,0.0002410523,0.001844251,0.0002790119,0.0002346847,0.00004466819,0.0006638485,0.00001264084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001685619,"about_ca_system_score_gemma":0.0003659305,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008314248,"about_ca_topic_score_gemma":0.0033729,"domain_scores_codex":[0.9961657,0.0003894238,0.001776237,0.0006335067,0.0005903341,0.0004447755],"domain_scores_gemma":[0.9965577,0.0005543602,0.0004366855,0.0005083714,0.00179083,0.0001521203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001663309,0.0005578967,0.02786561,0.006581151,0.001335646,0.000008093716,0.01662033,0.001234233,0.09518408,0.7704713,0.003011628,0.07546676],"study_design_scores_gemma":[0.0005277234,0.00258481,0.01114977,0.01077204,0.002494638,0.00006376675,0.2398472,0.244934,0.4753376,0.009731905,0.001835654,0.0007208014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3661938,0.001160886,0.6284896,0.0002243443,0.0006372955,0.002206898,0.00001497748,0.0001003671,0.0009718775],"genre_scores_gemma":[0.9959829,0.0001041528,0.0002416798,0.00002443223,0.0004174158,0.000578257,0.0002358339,0.00002709317,0.002388173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7607394,"threshold_uncertainty_score":0.9982895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2799693651166667,"score_gpt":0.5053688565051657,"score_spread":0.225399491388499,"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."}}