{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001540681,0.0002562093,0.000296848,0.001348249,0.0005219197,0.001526455,0.003888448,0.0003409447,0.0002588916],"category_scores_gemma":[0.0001359186,0.0003028117,0.00009502543,0.00233562,0.0001900066,0.0008588689,0.001318007,0.001556308,0.00005492554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005886024,"about_ca_system_score_gemma":0.0008355578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003104058,"about_ca_topic_score_gemma":0.000131078,"domain_scores_codex":[0.9962522,0.0006914829,0.0001206418,0.0008674012,0.001387899,0.0006803797],"domain_scores_gemma":[0.9985456,0.0002609695,0.0001255111,0.000526062,0.000302078,0.0002397321],"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":[0.00001457762,0.00008927519,0.00001873926,0.00003293152,0.0001322248,0.00007714552,0.0003684764,0.0001095334,0.000009726326,0.2168543,0.7749742,0.007318839],"study_design_scores_gemma":[0.0005774082,0.00005161465,0.000008714803,0.0004882769,0.00001373152,0.000001669695,0.000939422,0.0002189993,0.00002815287,0.001892727,0.9954271,0.0003522043],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00004380972,0.0002542343,0.1933342,0.02888106,0.0002365579,0.001111243,0.0001742155,0.0005193329,0.7754453],"genre_scores_gemma":[0.008233695,0.00004665365,0.02812338,0.00009818174,0.00009955431,0.000002570586,0.0001058324,0.00006788402,0.9632223],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2204529,"threshold_uncertainty_score":0.9999424,"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."}}