{"prediction": {"id": "19dc9a72-47dc-5258-9916-046835ec243c", "work_id": "561544a1-dea7-58ab-8965-f5310bdacb87", "study_id": "ccde4d71-0c36-50d2-9d65-8a60e29ed37e", "kind": "Model evaluation", "pages": [5], "version": "Version of record", "source_work_id": "561544a1-dea7-58ab-8965-f5310bdacb87", "title": "Accelerating virtual patient generation with a Bayesian optimization and machine learning surrogate model.", "doi": "10.1002/psp4.13288", "pdf_sha256": "851924d4734cd89ea25c7d399adb757b6787fc7d55e5c4ea28adae37ac5c94f3", "physical_page_count": 9}, "fields": {"endpoint": {"value": "virtual_cohort_size", "source_basis": "original_pdf_review", "pages": [5]}, "family": {"value": "cohort_coverage", "source_basis": "verified_profile", "pages": [5]}, "measured_variable": {"value": "virtual_cohort_size", "source_basis": "original_pdf_review", "pages": [5]}}, "endpoints": [{"term": "cohort_coverage", "label": "Cohort size and coverage"}, {"term": "optimization", "label": "Optimization performance"}], "validations": [{"id": "41b5b74c-e938-5029-9550-86b4f65aa47b", "claim_id": "19dc9a72-47dc-5258-9916-046835ec243c", "coverage": "direct_comparison", "support": "supports", "source": "same_source", "overlap": "overlap", "comparability": "matched", "statistics": "not_applicable", "anchors": [{"work_id": "561544a1-dea7-58ab-8965-f5310bdacb87", "version": "Version of record", "pages": [5, 7]}]}], "model_resources": {"total": 0, "page": 1, "limit": 50, "rows": [], "review_status": "indexed_source"}}