{"id":"W4415602683","doi":"10.36227/techrxiv.176162061.19169845/v1","title":"MaplePT: A Generalized Instruction-Tuned Canadian Language Model Trained on Distributed Low-Cost Compute","year":2025,"lang":"","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Leverage (statistics); Cloud computing; Natural language; Language model; Inference; Scaling; Fluency; Quantization (signal processing)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000472509,0.001184704,0.0004810489,0.0004401913,0.001099405,0.001179052,0.002393194,0.0007308787,0.006786904],"category_scores_gemma":[0.002067392,0.0004369267,0.0009467608,0.0008112399,0.0006519514,0.001341967,0.0008908097,0.002435098,0.002630269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004535225,"about_ca_system_score_gemma":0.009911479,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6277694,"about_ca_topic_score_gemma":0.7446643,"domain_scores_codex":[0.9997093,0.00002731906,0.000009038706,0.0001082823,0.00007612294,0.00006990531],"domain_scores_gemma":[0.9995401,0.0001278507,0.00001171014,0.00006283265,0.0002087349,0.00004880454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007358794,0.0002362919,0.005302487,0.0003118,0.0002788464,0.0003926013,0.0004730871,0.5564458,0.01959584,0.01110446,0.1500754,0.2550475],"study_design_scores_gemma":[0.00004598912,0.00004839778,0.000789067,0.00001038051,0.00002574359,0.00003736771,0.000090054,0.9803073,0.004751452,0.002132782,0.01173093,0.00003062344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3441994,0.001475229,0.4317084,0.003351517,0.001220648,0.0008948736,0.02609663,0.1351509,0.05590234],"genre_scores_gemma":[0.6805158,0.0004905146,0.2370046,0.001015405,0.00007086556,0.0005186309,0.03828425,0.003856155,0.0382437],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3722306,"threshold_uncertainty_score":0.7488455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01089164059948473,"score_gpt":0.2682301032324463,"score_spread":0.2573384626329616,"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."}}