{"prediction": {"id": "3208f46a-aa3d-58b4-9836-c11c5262568c", "work_id": "194fead6-52fc-55fd-9ce6-525ccac3b1df", "study_id": "a230b194-f0fc-5382-9bcc-e9e6919d8e5c", "kind": "Model evaluation", "pages": [7], "version": "Version of record", "source_work_id": "194fead6-52fc-55fd-9ce6-525ccac3b1df", "title": "A myoelectric digital twin for fast and realistic modelling in deep learning.", "doi": "10.1038/s41467-023-37238-w", "pdf_sha256": "1ab434bbeebbab0ad6abc5ad6f39b5e41051b421ba1fd162d6800ac1d58bd531", "physical_page_count": 15}, "fields": {"comparator": {"value": "experimental_or_observational_reference", "source_basis": "verified_profile", "pages": [7]}, "endpoint": {"value": "surface_emg_motor_unit_discharge_events__rate_of_agreement", "source_basis": "verified_profile", "pages": [7]}, "family": {"value": "agreement", "source_basis": "verified_profile", "pages": [7]}, "measured_variable": {"value": "surface_emg_motor_unit_discharge_events", "source_basis": "verified_profile", "pages": [7]}, "measurement_role": {"value": "reference_agreement", "source_basis": "original_pdf_review", "pages": [7]}, "metric": {"value": "rate_of_agreement", "source_basis": "verified_profile", "pages": [7]}, "population": {"value": "human_observations", "source_basis": "verified_profile", "pages": [1, 7]}, "reference_type": {"value": "alternative_computational_methods", "source_basis": "verified_profile", "pages": [7]}, "role": {"value": "model_fit", "source_basis": "verified_profile", "pages": [7]}, "scenario": {"value": "alternative_computational_methods", "source_basis": "verified_profile", "pages": [7]}}, "endpoints": [{"term": "agreement", "label": "Correlation or agreement"}], "validations": [{"id": "57795aa6-e447-59c2-982d-466653b720c8", "claim_id": "3208f46a-aa3d-58b4-9836-c11c5262568c", "coverage": "direct_comparison", "support": "supports", "source": "same_source", "overlap": "overlap", "comparability": "matched", "statistics": "significant", "anchors": [{"work_id": "194fead6-52fc-55fd-9ce6-525ccac3b1df", "version": "Version of record", "pages": [7, 13]}]}], "model_resources": {"total": 1, "page": 1, "limit": 50, "rows": [{"id": 536, "work_id": "194fead6-52fc-55fd-9ce6-525ccac3b1df", "claim_id": "3208f46a-aa3d-58b4-9836-c11c5262568c", "kind": "model", "label": "Myoelectric digital twin simulation software", "repository": "Author access on request", "identifier": "Myoelectric Digital Twin", "source_page": 13, "availability": "author_reported_restricted", "url": "https://www.nature.com/articles/s41467-023-37238-w", "scope": "related_reference", "resource_version": null, "version_basis": null, "repository_commit": null, "repository_member": null, "source_file_sha256": null, "source_basis": "legacy_curated_resource", "priority": 2, "doi": "10.1038/s41467-023-37238-w", "title": "A myoelectric digital twin for fast and realistic modelling in deep learning.", "version": "Version of record", "pdf_sha256": "1ab434bbeebbab0ad6abc5ad6f39b5e41051b421ba1fd162d6800ac1d58bd531", "association_scope": "prediction", "resource_relation": "related_reference", "source_review": {"indexed": true, "source_basis": "legacy_curated_resource"}}], "review_status": "indexed_source"}}