{"id":"W4417323839","doi":"10.5194/ica-abs-10-30-2025","title":"Semantic search engine for geospatial datasets using large language models and AWS OpenSearch","year":2025,"lang":"en","type":"article","venue":"Abstracts of the ICA","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Natural Resources Canada","funders":"","keywords":"Geospatial analysis; Semantics (computer science); Language model; Key (lock); Search engine; Field (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":[0.001438856,0.00005546417,0.0001223174,0.00007507204,0.000499702,0.00004754469,0.0002418607,0.00004876948,0.000007855066],"category_scores_gemma":[0.0001930011,0.00004285045,0.00003936743,0.000197142,0.0001505145,0.0002432267,0.0001763133,0.00007997494,0.000001567553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001714812,"about_ca_system_score_gemma":0.0001000178,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008579543,"about_ca_topic_score_gemma":0.00335319,"domain_scores_codex":[0.9991453,0.0000530579,0.0002055818,0.00008803197,0.0002629888,0.0002450145],"domain_scores_gemma":[0.9993835,0.0002133456,0.00006964166,0.0001863052,0.0001168225,0.00003040293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004101493,0.0008844122,0.01827484,0.004978675,0.001702127,0.00001968215,0.4693748,0.03566264,0.004167498,0.3610737,0.06284749,0.04060403],"study_design_scores_gemma":[0.01028901,0.0002602457,0.1846267,0.00306803,0.0006972417,0.00002151467,0.3517889,0.1421268,0.01287228,0.03699206,0.2553103,0.001946979],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9826365,0.0006686919,0.0017859,0.003813553,0.0003810032,0.001089802,0.0005008951,0.00002500874,0.009098618],"genre_scores_gemma":[0.9987521,0.00003196538,0.0004649859,0.00007653775,0.00003899675,0.000007833131,0.0000118526,0.000003116349,0.0006126073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3240816,"threshold_uncertainty_score":0.9980224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04076124191082959,"score_gpt":0.3689690373714755,"score_spread":0.3282077954606459,"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."}}