{"id":"W4366714876","doi":"10.22148/001c.74293","title":"Searching maps by words: how machine learning changes the way we explore map collections","year":2023,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Arts and Humanities Research Council; Alan Turing Institute; Austrian Institute of Technology; University of Minnesota; University of Southern California","keywords":"Interactivity; Mind map; Computer science; Curiosity; Interface (matter); Information retrieval; World Wide Web; Visualization; Beauty; Annotation; Artificial intelligence; Art","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009343608,0.0007150665,0.0008346507,0.006327257,0.003991535,0.02267768,0.003587401,0.002527436,0.01155108],"category_scores_gemma":[0.05445703,0.000805609,0.001187808,0.007509178,0.01110621,0.04027864,0.009537635,0.003635978,0.005313316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001985872,"about_ca_system_score_gemma":0.001746443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00806486,"about_ca_topic_score_gemma":0.01124792,"domain_scores_codex":[0.9916667,0.005365927,0.0003197483,0.001213439,0.0011551,0.0002790212],"domain_scores_gemma":[0.968908,0.02469331,0.0005854653,0.003766659,0.001328571,0.0007179703],"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":[0.0002047087,0.0001920284,0.008420319,0.0007454498,0.0001386736,0.0003304239,0.08280563,0.005938157,0.002394647,0.2597643,0.06624611,0.5728196],"study_design_scores_gemma":[0.00005173526,0.00005493247,0.002727565,0.0004622605,0.0000612878,0.0003036515,0.02439692,0.01964691,0.002056122,0.6507487,0.29935,0.0001399319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09599727,0.006782682,0.6307425,0.07889934,0.001318964,0.0002680909,0.002045732,0.01382612,0.1701193],"genre_scores_gemma":[0.4063898,0.004089755,0.5575535,0.005020524,0.0005951786,0.0003941187,0.001804872,0.004598747,0.01955349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02267768,"threshold_uncertainty_score":0.04941434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08158655033373287,"score_gpt":0.3221743146279093,"score_spread":0.2405877642941764,"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."}}