{"id":"W4411267758","doi":"10.22318/icls2025.100255","title":"A Systematic Literature Review of Large Language Model Applications in the Algebra Domain","year":2025,"lang":"en","type":"article","venue":"Proceedings.","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Algebra over a field; Programming language; Domain (mathematical analysis); Mathematics; Pure mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0008590386,0.0000755799,0.0001927567,0.00008447871,0.00003978112,0.00006891863,0.000879848,0.00003437636,6.395134e-7],"category_scores_gemma":[0.00008756053,0.00004780691,0.00004696664,0.0009020428,0.000007695562,0.0001707949,0.0001223291,0.0001235626,0.000001710778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001856582,"about_ca_system_score_gemma":0.00002776079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.193225e-7,"about_ca_topic_score_gemma":7.927001e-7,"domain_scores_codex":[0.9992098,0.00001560267,0.0002918061,0.0001867796,0.0001692404,0.0001267454],"domain_scores_gemma":[0.9994916,0.00003097842,0.00009372371,0.0002789297,0.00009122972,0.00001350908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[2.194328e-7,0.00003112602,0.00004752927,0.1119934,0.000005249378,5.882694e-7,0.006455755,0.00000295087,0.00008734368,0.8808424,0.0003920421,0.0001413786],"study_design_scores_gemma":[0.0004764082,0.00001795868,0.00009085074,0.3363302,0.00006376534,0.00002329128,0.002515146,0.585332,0.0004457185,0.07362522,0.0007590748,0.0003203347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002332588,0.123544,0.8554974,0.002592392,0.00003071823,0.001698481,0.000003660775,0.00008247269,0.01421834],"genre_scores_gemma":[0.8494144,0.005916565,0.1336007,0.008725536,0.00005584997,0.001639888,0.000005498725,0.00001314397,0.0006283788],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8470818,"threshold_uncertainty_score":0.1949509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00780541389418628,"score_gpt":0.27125327806474,"score_spread":0.2634478641705537,"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."}}