{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009980551,0.0000600297,0.00007531564,0.0001796324,0.0001456003,0.000215631,0.0005516653,0.00003608577,0.0002393787],"category_scores_gemma":[0.00009257489,0.00005430253,0.00002918465,0.0008382266,0.00005667491,0.0006189686,0.0001526818,0.00003391094,0.0002399569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002826984,"about_ca_system_score_gemma":0.00007730143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009668339,"about_ca_topic_score_gemma":0.00002200763,"domain_scores_codex":[0.9990454,0.00002717648,0.0002185568,0.0003602817,0.0002159135,0.0001326948],"domain_scores_gemma":[0.9987481,0.0000488118,0.00006527913,0.0007605352,0.0002710054,0.0001062658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001848033,0.0008490158,0.03767681,0.00002802635,0.000163673,0.000004945635,0.007222746,0.002309735,0.1461971,0.546896,0.09192432,0.1667092],"study_design_scores_gemma":[0.0001320881,0.00003101113,0.05844679,0.00001992577,0.000007549386,0.000001787424,0.00002652457,0.9268952,0.006109026,0.004479873,0.003734056,0.0001161738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4928164,0.00002113513,0.5014036,0.001253811,0.0007096126,0.0001291582,0.00001055469,0.001191142,0.002464629],"genre_scores_gemma":[0.9575227,2.261442e-7,0.04044278,0.00006590495,0.00002680114,0.00000904498,0.00001510889,0.000003872478,0.001913594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9245855,"threshold_uncertainty_score":0.3084241,"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."}}