{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01098667,0.001382473,0.001187208,0.00219387,0.0008722574,0.002906113,0.002864101,0.001958874,0.002613454],"category_scores_gemma":[0.05454201,0.000633936,0.001058016,0.002149423,0.001363355,0.008461502,0.004308305,0.002081732,0.001325043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002041989,"about_ca_system_score_gemma":0.001858146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04365546,"about_ca_topic_score_gemma":0.03585339,"domain_scores_codex":[0.9914904,0.005040954,0.0006409065,0.001103172,0.001367021,0.0003575942],"domain_scores_gemma":[0.941658,0.04894247,0.0008097386,0.004626404,0.00284732,0.001116035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01420708,0.003141837,0.09316672,0.00460625,0.001416855,0.001810093,0.02511856,0.3082905,0.01581731,0.03479642,0.09854064,0.3990878],"study_design_scores_gemma":[0.0004053788,0.0007386,0.009729183,0.0001150284,0.0002038707,0.0003526956,0.003785556,0.9532375,0.005815917,0.01109544,0.01431266,0.0002081444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8994257,0.002120381,0.04873965,0.002379044,0.0004846755,0.0005504623,0.006891743,0.02356231,0.01584612],"genre_scores_gemma":[0.9433019,0.000399056,0.04223089,0.0004885079,0.0001004481,0.0002980122,0.01007219,0.0007190523,0.002389955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04365546,"threshold_uncertainty_score":0.08680272,"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."}}