{"id":"W1792017449","doi":"10.22230/src.2017v8n2a280","title":"Guessing at the Content of a Million Books","year":2017,"lang":"en","type":"article","venue":"Scholarly and Research Communication","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Graffiti; Scholarship; Computer science; Reading (process); Context (archaeology); Set (abstract data type); Hypertext; Conjecture; Artificial intelligence; World Wide Web; Natural language processing; Linguistics; History; Mathematics; Programming language; Law; Philosophy","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001913032,0.0007326426,0.0005984874,0.009021102,0.003225724,0.0100301,0.001065181,0.002072327,0.05242914],"category_scores_gemma":[0.03641075,0.001229723,0.0006741905,0.005970296,0.002636192,0.02719089,0.002149565,0.002533053,0.0272605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001827658,"about_ca_system_score_gemma":0.001457974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003933718,"about_ca_topic_score_gemma":0.006352169,"domain_scores_codex":[0.9983358,0.0003544115,0.000151819,0.0002820215,0.0007667879,0.0001092255],"domain_scores_gemma":[0.9893828,0.004559083,0.0006782181,0.00116577,0.003603713,0.0006103486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003251327,0.0001345935,0.01595261,0.0010853,0.0002100125,0.0008485756,0.006034143,0.001187756,0.003764043,0.1156837,0.3561361,0.4986381],"study_design_scores_gemma":[0.00004189548,0.0001167241,0.01802718,0.003199717,0.000198519,0.001988746,0.01585738,0.005279803,0.004899196,0.2043698,0.7457987,0.000222479],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.202206,0.06465095,0.07155807,0.1176673,0.01313174,0.0004103204,0.01643608,0.006081187,0.5078583],"genre_scores_gemma":[0.6110238,0.03222352,0.09757971,0.01268303,0.006172922,0.0002713637,0.01417391,0.004452594,0.2214191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9899699,"threshold_uncertainty_score":0.1753929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4324220114255007,"score_gpt":0.3838589719409515,"score_spread":0.04856303948454915,"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."}}