{"id":"W2983102021","doi":"10.48550/arxiv.1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Kepler; Embedding; Computer science; Benchmark (surveying); Representation (politics); Language model; Natural language processing; Construct (python library); ENCODE; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002470151,0.0002364469,0.0002913406,0.0002179616,0.0001061055,0.000128404,0.0009295941,0.0002276933,0.000003112186],"category_scores_gemma":[0.0000635375,0.0002817158,0.0001345043,0.0002058554,0.00003657284,0.0003660831,0.001384307,0.0002699897,0.000007951076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001194546,"about_ca_system_score_gemma":0.0001805919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007708612,"about_ca_topic_score_gemma":0.00004294001,"domain_scores_codex":[0.9982482,0.00006977282,0.0001866838,0.001149964,0.00006081957,0.0002845113],"domain_scores_gemma":[0.9982934,0.0001804254,0.0001801017,0.001115082,0.0001261241,0.0001048933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002678032,0.00002948103,0.0002502917,0.0001681202,0.00004221702,0.00001257319,0.004922321,0.9101406,0.0001471246,0.08274837,0.0000822557,0.001429856],"study_design_scores_gemma":[0.0006246734,0.00001975912,0.0001007483,0.00007494826,0.00004138559,0.000001830081,0.0002099858,0.9762682,0.00007877564,0.02226474,0.00002605892,0.0002889376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.258843,0.00007209491,0.7390459,0.00004422949,0.0002465977,0.0005198103,0.0000120133,0.0001729629,0.001043338],"genre_scores_gemma":[0.9663846,0.00003979882,0.02675695,0.00003649318,0.00006486654,0.000003566427,0.0000208227,0.00001871523,0.006674208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.712289,"threshold_uncertainty_score":0.9999635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1069525455988214,"score_gpt":0.2532121545973456,"score_spread":0.1462596089985242,"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."}}