{"prediction": {"id": "19a828e5-6e2f-5d5f-9425-e15df0522541", "work_id": "fdb5539c-1310-5617-a04a-c518213f423b", "study_id": "1122cdcd-7642-53ae-80de-00722ff663ea", "kind": "Model evaluation", "pages": [8], "version": "Version of record", "source_work_id": "fdb5539c-1310-5617-a04a-c518213f423b", "title": "TumorTwin: a Python framework for patient-specific digital twins in oncology.", "doi": "10.1186/s12911-026-03520-2", "pdf_sha256": "68ee32a980ed448939e3e558eaa32c8f4969acd693c089635a698e6af2bdc7ee", "physical_page_count": 16}, "fields": {"comparator": {"value": "experimental_or_observational_reference", "source_basis": "verified_profile", "pages": [8]}, "endpoint": {"value": "synthetic_tumor_model_parameters__relative_error", "source_basis": "verified_profile", "pages": [8]}, "family": {"value": "prediction_error", "source_basis": "verified_profile", "pages": [8]}, "measured_variable": {"value": "synthetic_tumor_model_parameters", "source_basis": "verified_profile", "pages": [8]}, "measurement_role": {"value": "prediction_error", "source_basis": "original_pdf_review", "pages": [8]}, "metric": {"value": "relative_error", "source_basis": "original_pdf_review", "pages": [8]}, "population": {"value": "simulated_system", "source_basis": "verified_profile", "pages": [1, 8]}, "reference_type": {"value": "synthetic_reference", "source_basis": "verified_profile", "pages": [8]}, "reported_time_window": {"value": "the first five synthetic imaging visits used for parameter-recovery calibration", "source_basis": "original_pdf_review", "pages": [8]}, "role": {"value": "prediction_error", "source_basis": "verified_profile", "pages": [8]}, "scenario": {"value": "synthetic_parameter_recovery", "source_basis": "verified_profile", "pages": [8]}, "unit": {"value": "dimensionless", "source_basis": "verified_profile", "pages": [8]}}, "endpoints": [{"term": "prediction_error", "label": "Prediction or fitting error"}], "validations": [{"id": "bf49ee40-4395-53f8-853a-5e3e8299036b", "claim_id": "19a828e5-6e2f-5d5f-9425-e15df0522541", "coverage": "direct_comparison", "support": "supports", "source": "same_source", "overlap": "overlap", "comparability": "matched", "statistics": "not_reported", "anchors": [{"work_id": "fdb5539c-1310-5617-a04a-c518213f423b", "version": "Version of record", "pages": [8]}]}], "model_resources": {"total": 1, "page": 1, "limit": 50, "rows": [{"id": 598, "work_id": "fdb5539c-1310-5617-a04a-c518213f423b", "claim_id": "19a828e5-6e2f-5d5f-9425-e15df0522541", "kind": "model", "label": "TumorTwin high-grade glioma calibration demonstration", "repository": "Author project documentation", "identifier": "TumorTwin HGG Demo", "source_page": 14, "availability": "author_reported_available", "url": "https://oncologymodelinggroup.github.io/TumorTwin/tutorials/HGG_Demo/", "scope": "claim_specific", "resource_version": null, "version_basis": null, "repository_commit": null, "repository_member": null, "source_file_sha256": null, "source_basis": "legacy_curated_resource", "priority": 2, "doi": "10.1186/s12911-026-03520-2", "title": "TumorTwin: a Python framework for patient-specific digital twins in oncology.", "version": "Version of record", "pdf_sha256": "68ee32a980ed448939e3e558eaa32c8f4969acd693c089635a698e6af2bdc7ee", "association_scope": "prediction", "resource_relation": "indexed_resource", "source_review": {"indexed": true, "source_basis": "legacy_curated_resource"}}], "review_status": "indexed_source"}}