{"id":"W7093102778","doi":"10.5281/zenodo.17403825","title":"My First LM: Teaching N-gram Language Models from Scratch","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":"Scratch; Software; Modeling language; Work (physics); Language model; Studio; Grid","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","open_science","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002292831,0.0006961848,0.0006321642,0.000856903,0.007913524,0.007146094,0.006126016,0.0004599732,0.02316544],"category_scores_gemma":[0.001502727,0.0007817326,0.0002611422,0.0009761125,0.0002954082,0.0006945551,0.006144383,0.002965411,0.01719985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004000204,"about_ca_system_score_gemma":0.00003329063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001741124,"about_ca_topic_score_gemma":0.000007455296,"domain_scores_codex":[0.9929822,0.002131487,0.0007008924,0.001970699,0.001044601,0.001170127],"domain_scores_gemma":[0.9962978,0.000171322,0.0005113856,0.002138724,0.0004204447,0.0004602714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002597476,0.0002662273,0.000001401522,0.0001452198,0.0001820797,0.00006014134,0.01555801,0.0009795635,0.00005887617,0.01092192,0.2708946,0.700906],"study_design_scores_gemma":[0.0006700491,0.0002230079,0.00002690633,0.0008680124,0.00006753444,0.00001857867,0.001034135,0.02682794,0.00001423675,0.0006255191,0.9688952,0.0007288576],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002294115,0.001043088,0.4872043,0.00194135,0.0006475823,0.000757643,0.0003046565,0.003499515,0.5043725],"genre_scores_gemma":[0.2483419,0.0007878338,0.08744323,0.001951551,0.003377141,5.407007e-7,0.008042331,0.02185077,0.6282048],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7001771,"threshold_uncertainty_score":0.9994634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02744775717346719,"score_gpt":0.2566514065358746,"score_spread":0.2292036493624074,"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."}}