{"id":"W4406094712","doi":"10.1080/00330124.2024.2434455","title":"Comparing the Spatial Querying Capacity of Large Language Models: OpenAI’s ChatGPT and Google’s Gemini Pro","year":2025,"lang":"en","type":"article","venue":"The Professional Geographer","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Geography; World Wide Web","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":[0.0009884051,0.0001303365,0.0001837113,0.00006766914,0.0003788714,0.00005818577,0.001011333,0.00005879775,0.00001144931],"category_scores_gemma":[0.00002883994,0.00007015083,0.00006614003,0.0002772126,0.0001199274,0.0002178168,0.001096388,0.0003065457,0.000001844963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013002,"about_ca_system_score_gemma":0.00006695704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008564076,"about_ca_topic_score_gemma":0.0002387992,"domain_scores_codex":[0.9987178,0.0001952314,0.0002517565,0.0002787843,0.0002863127,0.0002701551],"domain_scores_gemma":[0.9989867,0.0001869057,0.0001145608,0.0006128083,0.00006452417,0.00003455552],"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":[0.0001082356,0.0004680673,0.1056566,0.0003872567,0.000307568,0.000007211574,0.06028462,0.003455978,0.004049334,0.7835212,0.001459243,0.04029466],"study_design_scores_gemma":[0.0008578003,0.00002028644,0.03337344,0.0004633644,0.00003639195,0.000006361354,0.002285279,0.9129449,0.001850883,0.04726123,0.0006466032,0.0002534262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7708418,0.001035032,0.220019,0.003265162,0.0005538951,0.0005037967,0.00000438784,0.00006836057,0.003708628],"genre_scores_gemma":[0.9949104,0.00001246587,0.003601999,0.0006153971,0.00004508068,0.00004977988,0.000001102279,0.000005768641,0.0007580427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.909489,"threshold_uncertainty_score":0.2914011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03603262636662022,"score_gpt":0.2943405752862939,"score_spread":0.2583079489196737,"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."}}