{"id":"W4280563382","doi":"10.1007/s13222-022-00414-1","title":"An Ever-Expanding Humanities Knowledge Graph: The Sphaera Corpus at the Intersection of Humanities, Data Management, and Machine Learning","year":2022,"lang":"en","type":"article","venue":"Datenbank-Spektrum","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Berlin Center for Machine Learning; Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; Korea University","keywords":"Intersection (aeronautics); Digital humanities; Period (music); Humanities; Knowledge transfer; Graph; Computer science; Artificial intelligence; Data science; Geography; Art; Cartography; Knowledge management; Theoretical computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002427975,0.0001225533,0.0001635045,0.0001278347,0.003979233,0.0001541402,0.0008566433,0.00002094933,0.00118626],"category_scores_gemma":[0.00004302771,0.00008707303,0.00005915874,0.000443459,0.000465458,0.0003209231,0.001172415,0.0002562771,0.000005692702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001104877,"about_ca_system_score_gemma":0.00003095457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003678031,"about_ca_topic_score_gemma":0.01479072,"domain_scores_codex":[0.997636,0.001178449,0.0002500594,0.0003139024,0.0003965304,0.0002250295],"domain_scores_gemma":[0.9989523,0.0003695479,0.0002015045,0.000396892,0.00005042153,0.0000293797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002684431,0.0004436908,0.0540278,0.0001256268,0.001183445,0.00002885171,0.1414578,0.001894564,0.0003839074,0.6164881,0.01234326,0.1713545],"study_design_scores_gemma":[0.0004811165,0.0001770099,0.01397252,0.00002113467,0.0003172149,0.00001303697,0.0768906,0.0100486,0.00005012709,0.01647225,0.8812389,0.0003174571],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8956499,0.00756248,0.005251118,0.001355687,0.002158502,0.0009670416,0.000611425,0.0002490271,0.08619487],"genre_scores_gemma":[0.986831,0.000222687,0.000142898,0.0001328178,0.0001700878,0.00002120574,0.0006380469,0.00001386065,0.01182738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8688956,"threshold_uncertainty_score":0.9997268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1315359856708628,"score_gpt":0.3591665838394898,"score_spread":0.227630598168627,"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."}}