{"id":"W4379197269","doi":"10.1186/s12859-023-05350-9","title":"An analysis of entity normalization evaluation biases in specialized domains","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Computer science; Data science; Task (project management); Natural language processing; Field (mathematics); Information retrieval; Artificial intelligence; 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":[0.001343168,0.00006681481,0.0001690828,0.0008837858,0.00003752672,0.00007107916,0.0003668019,0.00004578007,0.00002414729],"category_scores_gemma":[0.0002453123,0.00006555396,0.00006223541,0.002977396,0.00001512778,0.0009311667,0.00008191245,0.00003287282,0.00001828852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006379598,"about_ca_system_score_gemma":0.0001060125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008450645,"about_ca_topic_score_gemma":0.0008904817,"domain_scores_codex":[0.9986913,0.00008063784,0.0004965225,0.0001052493,0.0004732173,0.0001531016],"domain_scores_gemma":[0.9990909,0.00008147532,0.0001857267,0.0004819432,0.0001218707,0.00003807071],"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":[0.000002792433,0.00003358802,0.04669656,0.00003630481,0.00002714025,3.205768e-7,0.003554263,0.9318874,0.00002967858,0.008390349,0.00002598205,0.009315601],"study_design_scores_gemma":[0.0002545407,0.00001258362,0.08200925,0.00001091109,0.00005625054,1.813143e-7,0.000214045,0.9168553,0.0001058857,0.0003971131,0.00001785332,0.00006603594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3288236,0.000003613194,0.6704948,0.00001068862,0.00009216817,0.0001268814,0.000004487136,0.00006283563,0.0003808724],"genre_scores_gemma":[0.7675124,0.00001669245,0.2322336,0.00003839132,0.00002469095,0.00001055083,0.0001486638,0.000003345893,0.00001161969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4386888,"threshold_uncertainty_score":0.2673213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08364742459170624,"score_gpt":0.3394736568482408,"score_spread":0.2558262322565346,"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."}}