{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005746112,0.001395825,0.0004174982,0.0004661321,0.0005053017,0.001407407,0.001599154,0.001097004,0.2131267],"category_scores_gemma":[0.001968958,0.0005374344,0.0006088965,0.0004064123,0.0003849675,0.002659634,0.002105976,0.001285714,0.07183985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007710283,"about_ca_system_score_gemma":0.001054018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00148231,"about_ca_topic_score_gemma":0.002625727,"domain_scores_codex":[0.9997286,0.00004835828,0.000009896518,0.00008993897,0.00008575597,0.00003741003],"domain_scores_gemma":[0.9993846,0.0001826252,0.00002144857,0.0001277681,0.0001381959,0.0001453497],"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":[0.0003274554,0.0004564671,0.0005513337,0.000545496,0.00002235405,0.0003046846,0.0009678963,0.004271406,0.04249606,0.02577017,0.3938503,0.5304364],"study_design_scores_gemma":[0.0001686057,0.0005402111,0.0014561,0.0002426935,0.00003171504,0.0008438191,0.0004479697,0.04174205,0.06745331,0.02856669,0.858402,0.000104771],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0150316,0.0003367598,0.5988329,0.001284476,0.0008227574,0.000493884,0.005027983,0.06671196,0.3114576],"genre_scores_gemma":[0.08779868,0.0005292721,0.3784887,0.0006593638,0.0001410122,0.001053035,0.00882495,0.01653431,0.5059708],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.2131267,"threshold_uncertainty_score":0.7129799,"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."}}