{"id":"W2970591538","doi":"","title":"KlickLabs at the TAC 2018 Drug-drug Interaction Extraction from Drug Labels Track.","year":2018,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Drug; Track (disk drive); Drug-drug interaction; Extraction (chemistry); Computer science; Pharmacology; Chemistry; Medicine; Chromatography","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":[0.005480777,0.002360524,0.002129555,0.006896976,0.001351724,0.004810159,0.002304306,0.002031634,0.1004966],"category_scores_gemma":[0.01674953,0.0007678022,0.001587865,0.004358813,0.0004437484,0.005824937,0.003620613,0.002325868,0.1052355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00169943,"about_ca_system_score_gemma":0.002661197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009002505,"about_ca_topic_score_gemma":0.01674663,"domain_scores_codex":[0.9964953,0.0006422261,0.0002370259,0.0008826833,0.001443009,0.0002998484],"domain_scores_gemma":[0.9923497,0.00226347,0.0003405446,0.00192227,0.00234614,0.0007777323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003757347,0.0001921105,0.000912977,0.0004651462,0.0001098408,0.00009691462,0.00006257964,0.001178143,0.003745708,0.003212478,0.8536666,0.1359818],"study_design_scores_gemma":[0.0002739727,0.0002669179,0.003393949,0.000209903,0.0001566787,0.0002026661,0.0001221016,0.06458635,0.01472279,0.02346532,0.8924921,0.0001072636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.009395465,0.006691128,0.2160065,0.01105419,0.007609416,0.0008938528,0.4577799,0.2389031,0.05166641],"genre_scores_gemma":[0.04336859,0.002045974,0.2155238,0.001864743,0.001192827,0.0006499326,0.6408616,0.01098808,0.0835044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1004966,"threshold_uncertainty_score":0.3361946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007887684036896365,"score_gpt":0.2852766464164186,"score_spread":0.2773889623795223,"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."}}