{"id":"W3162334759","doi":"10.1200/jco.20.03613","title":"Updated Standardized Definitions for Efficacy End Points (STEEP) in Adjuvant Breast Cancer Clinical Trials: STEEP Version 2.0","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Breast Cancer Treatment Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":221,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"National Cancer Institute; National Institute for Health and Care Research","keywords":"Medicine; Breast cancer; Clinical endpoint; Cancer; Clinical trial; Oncology; Surrogate endpoint; Internal medicine; Adjuvant therapy; Surgery","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008827832,0.0002160465,0.002215695,0.00007666437,0.00008260208,0.00001570175,0.0002172991,0.0006238433,0.0002838381],"category_scores_gemma":[0.01183758,0.000167552,0.001244932,0.0001522599,0.0002623062,0.000013093,0.0001571044,0.0005646255,0.000007903409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001585726,"about_ca_system_score_gemma":0.002909196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002265577,"about_ca_topic_score_gemma":0.0004645675,"domain_scores_codex":[0.9925619,0.002631789,0.003781199,0.0004325147,0.0002623956,0.0003302335],"domain_scores_gemma":[0.9923134,0.00413377,0.002001131,0.0002748311,0.001001096,0.0002757777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.08036845,0.01081873,0.2042743,0.0000581386,0.005796866,0.0007108834,0.0001190156,0.0001797595,0.003452598,0.0002622035,0.1052306,0.5887285],"study_design_scores_gemma":[0.08068209,0.005312872,0.561619,0.000223144,0.001463585,0.0004005781,0.0004338447,0.00002617027,0.001952209,0.0006618125,0.3468325,0.0003921739],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965876,0.003734696,0.0007287351,0.02180363,0.005603756,0.0004572168,0.00112751,0.000009200459,0.0006591971],"genre_scores_gemma":[0.9782816,0.01152985,0.004760908,0.002374109,0.00271179,0.000032769,0.0001830751,0.00003422883,0.00009165574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5883363,"threshold_uncertainty_score":0.9964861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2333773198881165,"score_gpt":0.5225413800965529,"score_spread":0.2891640602084364,"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."}}