{"id":"W2952944718","doi":"10.18653/v1/w19-5004","title":"REflex: Flexible Framework for Relation Extraction in Multiple Domains","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; Mitacs","keywords":"Computer science; Relation (database); Field (mathematics); Data science; Artificial intelligence; Data mining; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0045313,0.00188845,0.001232898,0.007209437,0.001129605,0.004211308,0.002803248,0.002265197,0.02023111],"category_scores_gemma":[0.01182655,0.001203545,0.003889482,0.005004808,0.0008104295,0.007777772,0.005335672,0.003368786,0.01943514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103778,"about_ca_system_score_gemma":0.002163161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004714506,"about_ca_topic_score_gemma":0.01297324,"domain_scores_codex":[0.9968106,0.0008471822,0.0003163669,0.001214024,0.0006333294,0.0001784254],"domain_scores_gemma":[0.9965145,0.001628928,0.0002184987,0.001184102,0.0002988843,0.000155156],"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":[0.0003690165,0.0002267607,0.00322972,0.001969255,0.0004018201,0.0006525302,0.0009556994,0.01576424,0.009473379,0.08231401,0.1758965,0.708747],"study_design_scores_gemma":[0.0001480457,0.0001190478,0.003065169,0.0006034151,0.0002201196,0.001473817,0.0008295787,0.2959286,0.01422204,0.2439015,0.4393501,0.0001386046],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001790966,0.001117563,0.9371207,0.0006162202,0.0001168456,0.0002729132,0.009597111,0.04654932,0.002818302],"genre_scores_gemma":[0.04392413,0.0009019895,0.9198083,0.0004569493,0.0001428301,0.0005041125,0.02507304,0.002838271,0.00635036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02023111,"threshold_uncertainty_score":0.06767976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08271429853203008,"score_gpt":0.3507164476325503,"score_spread":0.2680021491005202,"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."}}