{"id":"W2768628715","doi":"","title":"Stacked Ensembles of Information Extractors for Knowledge-Base Population by Combining Supervised and Unsupervised Approaches","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Base (topology); Artificial intelligence; Knowledge base; Population; Machine learning; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007903825,0.00009552547,0.0001625223,0.0001059361,0.00008030557,0.00005233969,0.000259259,0.00005145381,5.638095e-7],"category_scores_gemma":[0.0001111696,0.00008922123,0.00001743318,0.0001792406,0.0001638234,0.0008504997,0.00009715345,0.00003494031,3.373067e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009455228,"about_ca_system_score_gemma":0.00004151966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002783748,"about_ca_topic_score_gemma":0.000001500672,"domain_scores_codex":[0.9993485,0.00006293472,0.0002764445,0.0001340723,0.0000826605,0.00009539903],"domain_scores_gemma":[0.9989656,0.0003557377,0.0001576635,0.0003143249,0.0001472641,0.00005942374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004290241,0.00005360503,0.0004402004,0.0001097195,0.00001000856,7.332714e-9,0.003929223,0.000003017024,0.0006624454,0.9204628,0.000233473,0.07405256],"study_design_scores_gemma":[0.001060828,0.0002824833,0.0007599178,0.00003783608,0.00004535821,0.000003430968,0.006316623,0.005290158,0.08080151,0.9020126,0.003103705,0.0002855179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2281521,0.0003747418,0.7703289,0.00005907347,0.00001487159,0.0004786285,0.0000780844,0.00009853379,0.0004150849],"genre_scores_gemma":[0.9653152,0.00001800183,0.03416274,0.000007976214,0.00001040032,0.0001778594,0.0002900688,0.00000494959,0.00001286108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7371631,"threshold_uncertainty_score":0.3638336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03865730491067035,"score_gpt":0.2641246425481397,"score_spread":0.2254673376374694,"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."}}