{"id":"W4416701898","doi":"10.1016/j.envsoft.2025.106792","title":"Advancing geospatial data infrastructure in Dataverse via metadata automation, interactive tools and LLM case study","year":2025,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Artificial Intelligence in Medicine (Canada)","funders":"Office of Advanced Cyberinfrastructure; Alfred P. Sloan Foundation; National Institutes of Health; National Science Foundation","keywords":"Geospatial analysis; Metadata; Geospatial metadata; Geospatial PDF; Metadata management; Meta Data Services; Reuse; Metadata modeling; Metadata repository","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":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0009112262,0.0002340365,0.0002285651,0.0002624066,0.0002399746,0.00156616,0.002291895,0.00004821803,0.00002512622],"category_scores_gemma":[0.0002697275,0.0002378423,0.00001816145,0.000294069,0.00006606167,0.05341303,0.007424796,0.0004111892,0.00001506095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001997215,"about_ca_system_score_gemma":0.0000451084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008568608,"about_ca_topic_score_gemma":0.0003570794,"domain_scores_codex":[0.9974205,0.0002627459,0.0003923239,0.001142106,0.0004338352,0.0003484328],"domain_scores_gemma":[0.9968272,0.0004886069,0.0001545849,0.002431371,0.000008697097,0.00008953656],"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":[0.0001666483,0.002426269,0.1121756,0.0002290353,0.0006763206,0.008367228,0.007944576,0.4024822,0.0001900872,0.001089643,0.00125731,0.4629951],"study_design_scores_gemma":[0.0008112903,0.00008517717,0.006212144,0.00004736354,0.00005067239,0.0001168506,0.003015761,0.9845209,0.00002997583,0.0005059712,0.004328914,0.0002749581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2006551,0.00007219408,0.798076,0.00007786453,0.0001163404,0.0006251367,0.0002890096,0.00007453417,0.00001387274],"genre_scores_gemma":[0.8348411,0.0001914398,0.164056,0.000111302,0.00001823661,0.0000302701,0.0006368608,0.00001296096,0.000101748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.634186,"threshold_uncertainty_score":0.9994703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04018958650219973,"score_gpt":0.3170950997399523,"score_spread":0.2769055132377526,"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."}}