{"id":"W7093082652","doi":"10.5281/zenodo.17410380","title":"My First Language Model: Understand how AI language models work by building one yourself.","year":2025,"lang":"","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","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; Modeling language; Language understanding; Language model; Universal Networking Language; Language technology; On Language","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","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001686518,0.000664644,0.0006032346,0.0008154973,0.004662755,0.006901111,0.004330226,0.0004366974,0.005566715],"category_scores_gemma":[0.0006705643,0.0007767809,0.0002150605,0.001698121,0.0003364694,0.0007184818,0.003763195,0.002043594,0.00189268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005622639,"about_ca_system_score_gemma":0.0000366698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001342064,"about_ca_topic_score_gemma":0.000002173164,"domain_scores_codex":[0.9944249,0.00101279,0.0004729462,0.001710557,0.001113729,0.001265042],"domain_scores_gemma":[0.9969269,0.00008874915,0.000435295,0.001683608,0.0004025184,0.0004629111],"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":[0.00006472607,0.0004065607,8.467379e-7,0.0004159457,0.0003113095,0.00005717306,0.03560052,0.01387495,0.0002444402,0.01578493,0.5083821,0.4248565],"study_design_scores_gemma":[0.0008127376,0.0001898162,0.000002342633,0.0009835394,0.00008612858,0.00002666445,0.002494245,0.09045231,0.00004873839,0.0001842606,0.903901,0.0008182001],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002199092,0.002289555,0.8683927,0.004460438,0.0002507058,0.0007604353,0.0002529389,0.002654121,0.1207192],"genre_scores_gemma":[0.4863586,0.0006699179,0.04084367,0.0009208291,0.0007864345,3.328525e-7,0.002318093,0.0117325,0.4563696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.827549,"threshold_uncertainty_score":0.9994683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03603181729306838,"score_gpt":0.2584947815310149,"score_spread":0.2224629642379465,"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."}}