{"id":"W2909027478","doi":"10.1145/3284869.3284892","title":"Automated Extraction of Symptoms related to Rare Diseases from Scientific Publications","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Exploit; Statistic; Focus (optics); Population; Task (project management); Term (time); Information extraction; Information retrieval; Data science; Medicine; Statistics; Computer security; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001489674,0.001085205,0.0009058866,0.01342582,0.0005564659,0.001878075,0.0007743838,0.001110665,0.00174392],"category_scores_gemma":[0.008162438,0.000302253,0.001232699,0.006914337,0.0002864824,0.002258955,0.001123542,0.0006270455,0.002165461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003858314,"about_ca_system_score_gemma":0.001630456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001488448,"about_ca_topic_score_gemma":0.001755767,"domain_scores_codex":[0.99854,0.000284097,0.0003355308,0.0003986771,0.0003527073,0.00008892265],"domain_scores_gemma":[0.9912856,0.004520227,0.001725834,0.0006577782,0.001575017,0.0002355052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003588548,0.0003337636,0.05441603,0.003283029,0.0003871322,0.003391313,0.001206376,0.003807367,0.06125331,0.004479296,0.03894991,0.8281336],"study_design_scores_gemma":[0.0002385163,0.0007845637,0.2814781,0.001230591,0.001998635,0.01447598,0.003131952,0.2430835,0.136744,0.0279296,0.2884646,0.0004398662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2887554,0.01705771,0.5718546,0.004092213,0.001518314,0.001247348,0.06844911,0.03116332,0.01586198],"genre_scores_gemma":[0.3797041,0.007601781,0.5289427,0.0004023075,0.001365103,0.0005335252,0.07554985,0.0005057206,0.00539481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01342582,"threshold_uncertainty_score":0.007878244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02034518079087244,"score_gpt":0.2870673585793582,"score_spread":0.2667221777884857,"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."}}