{"id":"W4399210979","doi":"10.1007/978-3-031-63028-6_6","title":"Preliminary Systematic Review of Open-Source Large Language Models in Education","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University; Simon Fraser University; Mount Saint Vincent University","funders":"","keywords":"Computer science; Open source; Programming language; Natural language processing; Artificial intelligence; Software engineering; Software","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"],"consensus_categories":[],"category_scores_codex":[0.002049797,0.0003681613,0.0009234578,0.0007574717,0.00005506746,0.0003609087,0.005242052,0.0001783159,0.000009161162],"category_scores_gemma":[0.0001315037,0.0003178997,0.000112413,0.0007339118,0.0001106824,0.000834158,0.003156382,0.0005925865,0.00002271811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002936169,"about_ca_system_score_gemma":0.0008959837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006938328,"about_ca_topic_score_gemma":0.00004317715,"domain_scores_codex":[0.9965782,0.00006483087,0.0009617807,0.001221547,0.0007733853,0.0004002507],"domain_scores_gemma":[0.9971949,0.0002756412,0.000376297,0.001899558,0.0001668524,0.00008678417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005630668,0.0001957005,0.000005663754,0.4435874,0.00003001856,0.0001277278,0.009576014,0.0500306,0.0000340547,0.3211671,0.00008094925,0.1751591],"study_design_scores_gemma":[0.0000701011,0.00004820085,0.000001009038,0.2415557,0.00002010065,0.00004658209,0.000001220693,0.6722984,0.00004721846,0.08557714,0.00004906726,0.0002852527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001532876,0.07487134,0.9180022,0.0005406998,0.0008971028,0.001443919,0.000003550951,0.00007010209,0.004155723],"genre_scores_gemma":[0.1804322,0.005659314,0.7926837,0.01211349,0.0006092603,0.0003345646,0.00002904624,0.0001802941,0.007958104],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6222678,"threshold_uncertainty_score":0.9999273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02051880195112533,"score_gpt":0.2858049584931694,"score_spread":0.2652861565420441,"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."}}