{"id":"W4388048690","doi":"10.1016/j.cancergen.2023.08.027","title":"19. Developing a generalized model for variants in CIViC","year":2023,"lang":"en","type":"article","venue":"Cancer Genetics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Computational biology; Biology; Gene; Genetics","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":[0.0001831953,0.0001024423,0.000124023,0.0001563694,0.00005805611,0.00007283925,0.000655857,0.00006826666,0.000001274173],"category_scores_gemma":[0.00004088691,0.0001004845,0.00002771748,0.0006915976,0.00001422203,0.00009718757,0.0002164259,0.00007068358,0.000003442426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001434401,"about_ca_system_score_gemma":0.0003469193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004206001,"about_ca_topic_score_gemma":0.0001173145,"domain_scores_codex":[0.9990903,0.00001568328,0.000165643,0.0003004648,0.000127008,0.0003009107],"domain_scores_gemma":[0.9995307,0.00003223992,0.00004941492,0.0002714958,0.00007046548,0.00004570948],"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":[0.00005198884,0.00007654741,0.004428952,0.0007657228,0.0000686053,0.00009754811,0.01342246,0.1084555,0.03567062,0.1823636,0.03656384,0.6180346],"study_design_scores_gemma":[0.0002398037,0.000009108494,0.0001916381,0.00004195964,0.000002260754,0.000001326633,0.000003008365,0.8936695,0.01038562,0.09444368,0.0008571959,0.0001548496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01643601,0.00356607,0.9780045,0.001090039,0.0002030477,0.0002331093,0.000007952061,0.0004371706,0.00002210152],"genre_scores_gemma":[0.1050156,0.0005653618,0.8927038,0.001012328,0.00007381798,0.0002347543,0.000004746218,0.00001718122,0.0003724775],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7852141,"threshold_uncertainty_score":0.4097638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0632904558404019,"score_gpt":0.3523352005773486,"score_spread":0.2890447447369467,"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."}}