{"id":"W2807400292","doi":"","title":"TinkerBell: Cross-lingual Cold-Start Knowledge Base Construction.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Base (topology); Computer science; Knowledge base; Artificial intelligence; Mathematics","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":[0.00288078,0.001207494,0.001194965,0.003119298,0.001519589,0.004128818,0.004811147,0.00192573,0.0409818],"category_scores_gemma":[0.01538933,0.001615466,0.002130044,0.002979042,0.001347213,0.006641787,0.00961405,0.003368724,0.02114539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162233,"about_ca_system_score_gemma":0.003259271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007179787,"about_ca_topic_score_gemma":0.01689534,"domain_scores_codex":[0.9972764,0.0006837455,0.0002517647,0.0006456762,0.0008593143,0.0002831757],"domain_scores_gemma":[0.9941332,0.002681976,0.0001595216,0.001673314,0.001116585,0.0002354258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006581369,0.000419081,0.002683898,0.001993935,0.0005080203,0.001312308,0.002133041,0.006419946,0.01287315,0.1155465,0.2829656,0.5724863],"study_design_scores_gemma":[0.000238083,0.0001781234,0.001776959,0.000705525,0.0003587949,0.0009270707,0.001736556,0.1253156,0.05820759,0.237604,0.5727032,0.0002484786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004013006,0.0005443302,0.8458421,0.0003587508,0.0003044498,0.0003573361,0.00578288,0.1275239,0.01527338],"genre_scores_gemma":[0.07686552,0.0006093377,0.8366255,0.0006193869,0.0001018238,0.0007046836,0.04024623,0.02148584,0.02274172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0409818,"threshold_uncertainty_score":0.1370978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208045681939296,"score_gpt":0.3062977349484454,"score_spread":0.2942172781290524,"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."}}