{"id":"W6947658562","doi":"10.48448/2b2k-qk12","title":"Learning to Extract Structured Entities Using Language Models","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Task (project management); Information extraction; Structured prediction; Field (mathematics); Language model; Set (abstract data type); Named-entity recognition; Code (set theory); Precision and recall; Source code","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":[0.002374989,0.002215249,0.001013783,0.003710787,0.000770052,0.003017629,0.00225915,0.001732882,0.006555822],"category_scores_gemma":[0.008856011,0.0007541264,0.002850538,0.00349707,0.0007803973,0.006125312,0.00274973,0.002413526,0.01096738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001120984,"about_ca_system_score_gemma":0.001956876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003794066,"about_ca_topic_score_gemma":0.009223195,"domain_scores_codex":[0.9980415,0.0006281953,0.000148299,0.0006995872,0.00037652,0.0001058707],"domain_scores_gemma":[0.9952952,0.002984499,0.0003163892,0.0007303673,0.0005494972,0.0001240487],"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":[0.0002320047,0.0002950536,0.004920817,0.001012361,0.0003592245,0.0007569942,0.0004802762,0.0984045,0.01145918,0.03822643,0.06753256,0.7763207],"study_design_scores_gemma":[0.0000338756,0.00007981326,0.0007557184,0.0001579183,0.0001152404,0.0004281055,0.0002765206,0.8564528,0.0109108,0.09710442,0.0336222,0.00006265636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007660381,0.001042455,0.9697927,0.001126159,0.0001349825,0.0002143849,0.005327063,0.01031854,0.004383272],"genre_scores_gemma":[0.1195387,0.001481107,0.8320592,0.0007793981,0.0002229783,0.000438062,0.03523508,0.001058572,0.009186799],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006555822,"threshold_uncertainty_score":0.02193141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02215105077893219,"score_gpt":0.2890545481242257,"score_spread":0.2669034973452935,"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."}}