Real-world variants labelled clinically relevant or VUS by the FoundationOne CDx report section they appear in.
These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.
Release 2026-10-09-ba02f2f4a36e · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
6 evaluations · 6 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: GPT-4o, basic prompt, temperature 1.0 (default) (Lin et al. 2025) | Protocol: Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS Dataset: FoundationOne CDx report variants, 612 patients (Lin et al. 2025) | 0.732 top-1-accuracy fraction · higher Uncertainty: 95% CI 0.7307 to 0.7329 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcegpt-4o-basic on foundationone (Lin et al. 2025) egfrnsclc-20261009-protocol-lin2025-foundationone-relevant-vs-vus Aggregation: Not reported Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification · Table 1 (Tab1), row 'Foundationone', column 'GPT-4o' Mean accuracy; 95% CI in the next column |
| Configuration: Llama 3.1 70B, basic prompt, temperature 0.8 (default) (Lin et al. 2025) | Protocol: Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS Dataset: FoundationOne CDx report variants, 612 patients (Lin et al. 2025) | 0.498 top-1-accuracy fraction · higher Uncertainty: 95% CI 0.4974 to 0.4978 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcellama-basic-t0-8 on foundationone (Lin et al. 2025) egfrnsclc-20261009-protocol-lin2025-foundationone-relevant-vs-vus Aggregation: Not reported Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification · Table 1 (Tab1), row 'Foundationone', column 'Llama 3' Mean accuracy; 95% CI in the next column |
| Configuration: Qwen 2.5 72B, basic prompt, temperature 0.8 (default) (Lin et al. 2025) | Protocol: Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS Dataset: FoundationOne CDx report variants, 612 patients (Lin et al. 2025) | 0.573 top-1-accuracy fraction · higher Uncertainty: 95% CI 0.5725 to 0.5736 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceqwen-basic on foundationone (Lin et al. 2025) egfrnsclc-20261009-protocol-lin2025-foundationone-relevant-vs-vus Aggregation: Not reported Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification · Table 1 (Tab1), row 'Foundationone', column 'Qwen 2.5' Mean accuracy; 95% CI in the next column |
| Configuration: Qwen 2.5 72B, binary class prompt, temperature 0.8 (default) (Lin et al. 2025) | Protocol: Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS Dataset: FoundationOne CDx report variants, 612 patients (Lin et al. 2025) | 0.612 top-1-accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceqwen-binary on foundationone (Lin et al. 2025) egfrnsclc-20261009-protocol-lin2025-foundationone-relevant-vs-vus Aggregation: Not reported Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification · Table 2 (Tab2), row 3 ('Qwen2.5', 'Binary class prompt + Default temperature (0.8)', 'FoundationOne'), column 'Accuracy' |
| Configuration: Qwen 2.5 72B, RAG with basic prompt, temperature 0.8 (default) (Lin et al. 2025) | Protocol: Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS Dataset: FoundationOne CDx report variants, 612 patients (Lin et al. 2025) | 0.662 top-1-accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceqwen-rag on foundationone (Lin et al. 2025) egfrnsclc-20261009-protocol-lin2025-foundationone-relevant-vs-vus Aggregation: Not reported Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification · Table 2 (Tab2), row 4 ('Qwen2.5', 'RAG + Default temperature (0.8)', 'FoundationOne'), column 'Accuracy' |
| Configuration: Qwen 2.5 72B, refined prompt, temperature 0.8 (default) (Lin et al. 2025) | Protocol: Lin et al. 2025 FoundationOne variants: clinically relevant vs VUS Dataset: FoundationOne CDx report variants, 612 patients (Lin et al. 2025) | 0.725 top-1-accuracy fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceqwen-refined on foundationone (Lin et al. 2025) egfrnsclc-20261009-protocol-lin2025-foundationone-relevant-vs-vus Aggregation: Not reported Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification · Table 2 (Tab2), row 2 ('Qwen2.5', 'Refined prompt + Default temperature (0.8)', 'FoundationOne'), column 'Accuracy' |
Source checking is not independent reproduction. Release 2026-10-09-ba02f2f4a36e.
A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
10 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.access Hospital data; not published Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.negatives 5266 Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.population 10,506 genetic alterations from 612 patients: 5,240 clinically relevant (Genomic Findings) and 5,266 VUS (appendix) Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.positives 5240 Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.private_data_not_included true Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.source_locator Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.total 10506 Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.version Single-hospital FoundationOne CDx reports as used by Lin et al. 2025 Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| description Real-world variants labelled clinically relevant or VUS by the FoundationOne CDx report section they appear in. Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| name FoundationOne CDx report variants, 612 patients (Lin et al. 2025) Context-only references | Benchmarking large language models GPT-4o, llama 3.1, and qwen 2.5 for cancer genetic variant classification Lin et al. 2025 Methods 'Dataset' (P35-P38), 'Model selection' (P39-P40), 'System prompts' (P41-P43), 'Testing framework design' (P44-P47) Version: npj Precision Oncology 9:141, published 2025-05-15; PMC12078457 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-10-09-ba02f2f4a36e · Record review: source checked
Stable ID: egfrnsclc-20261009-data-lin2025-foundationone-variants