{"id":"W7093080140","doi":"10.5281/zenodo.17403824","title":"LLMs Unplugged: Understand how AI language models work by building one yourself.","year":2025,"lang":"en","type":"other","venue":"ANU Open Research (Australian National University)","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cybernet Systems Corporation (Canada)","funders":"","keywords":"Work (physics); Software; Language model; Modeling language; Cybernetics; Studio","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":[0.0005430285,0.0006170239,0.0001916331,0.0004045443,0.000461099,0.002119356,0.0008088763,0.00109281,0.1016455],"category_scores_gemma":[0.002640758,0.0003350935,0.0003041449,0.0003066334,0.000670101,0.005798402,0.001686359,0.001299664,0.03867049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006712865,"about_ca_system_score_gemma":0.0007843295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002970298,"about_ca_topic_score_gemma":0.005758243,"domain_scores_codex":[0.9998065,0.0000585207,0.000008352877,0.00003682033,0.00006944867,0.00002039876],"domain_scores_gemma":[0.9995326,0.0002023425,0.00002137639,0.00006386827,0.0001048076,0.00007508344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001015301,0.0000938751,0.001144095,0.0004363749,0.00001143015,0.0003656469,0.004505951,0.003830425,0.006999747,0.132149,0.4664001,0.3839619],"study_design_scores_gemma":[0.0000174614,0.0000376539,0.0008269793,0.0002616253,0.000007984802,0.0003959789,0.0009326834,0.01668849,0.003581231,0.08301229,0.8942117,0.00002588754],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.009012783,0.001891073,0.4419539,0.01241173,0.0006679035,0.0001659082,0.002436626,0.0287644,0.5026958],"genre_scores_gemma":[0.1009067,0.002147934,0.2663771,0.003249814,0.0001690625,0.0003231515,0.003667721,0.009744173,0.6134144],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1016455,"threshold_uncertainty_score":0.3400382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.141618011911622,"score_gpt":0.3742661533082938,"score_spread":0.2326481413966718,"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."}}