{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.003774485,0.0002605809,0.0003884279,0.01143931,0.002300498,0.0036844,0.0009589362,0.001051475,0.005082204],"category_scores_gemma":[0.01232919,0.0002628491,0.0002682298,0.01834476,0.003007354,0.003558184,0.003312508,0.001502052,0.001420442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002900863,"about_ca_system_score_gemma":0.003358827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02052618,"about_ca_topic_score_gemma":0.04435825,"domain_scores_codex":[0.9972236,0.001058967,0.0002384411,0.0005555275,0.0008200703,0.0001034196],"domain_scores_gemma":[0.9804698,0.01503494,0.0008791459,0.001457353,0.001565732,0.0005930368],"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":[0.0003358051,0.0003576148,0.04084934,0.005655919,0.0002612573,0.004291537,0.03298929,0.007778481,0.008648466,0.1630703,0.33968,0.396082],"study_design_scores_gemma":[0.00003350911,0.00002048194,0.04431413,0.001553887,0.00005112811,0.0007374531,0.01304206,0.004903288,0.003110816,0.0252445,0.9069155,0.0000731727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5433224,0.03112659,0.05117567,0.04167442,0.00215053,0.0004357773,0.2455718,0.001848399,0.08269428],"genre_scores_gemma":[0.6717951,0.01153507,0.0795093,0.001842824,0.0006533606,0.0005756937,0.2202846,0.0009618243,0.01284224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9885607,"threshold_uncertainty_score":0.04081339,"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."}}