{"id":"W4401468895","doi":"10.1016/j.geomat.2024.100004","title":"Understanding the impact of geotagging on location inference models for accurate generalization to non-geotagged datasets","year":2024,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Geotagging; Inference; Generalization; Computer science; Geography; Data mining; Artificial intelligence; Information retrieval; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004086778,0.000103459,0.00009761392,0.0001433208,0.0001169435,0.0004448905,0.0005973442,0.00001861048,0.000005834238],"category_scores_gemma":[0.00005770568,0.00006844172,0.00004216797,0.0005684646,0.00001527182,0.0009201761,0.0001952419,0.00004070762,0.00002481021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008281305,"about_ca_system_score_gemma":0.00005353472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005311635,"about_ca_topic_score_gemma":0.000004469576,"domain_scores_codex":[0.9991637,0.0000240835,0.0001959786,0.0002422913,0.0001849772,0.0001889652],"domain_scores_gemma":[0.9991776,0.0001847416,0.00005578069,0.000510759,0.0000313603,0.00003979265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005492711,0.00002502198,0.000006469769,0.0001174107,0.00005428522,0.000001375317,0.0008178492,0.5768901,0.00008849405,0.3959016,0.01643268,0.009659227],"study_design_scores_gemma":[0.00008100928,0.00007590803,0.0001223373,0.0001369084,0.000010574,4.623649e-7,0.00003204556,0.9590775,0.0001000929,0.0401727,0.0001054688,0.00008496297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001806093,0.00001435123,0.9961837,0.000868502,0.0001539929,0.0004469432,0.0001166562,0.00007100393,0.0003387874],"genre_scores_gemma":[0.9898741,0.000007506812,0.009604068,0.0001149973,0.00004133863,0.00004113896,0.0002393255,0.000008058476,0.00006950949],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.988068,"threshold_uncertainty_score":0.4290089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1157011618042064,"score_gpt":0.3475959528579116,"score_spread":0.2318947910537051,"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."}}