| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.3 Accuracy fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Fig1c Overall Accuracy; Section 3 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.75 Micro F1 (evidence type: diagnostic) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Figure 1c, diagnostic row, alone column |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0 F1 (class: diagnostic negative) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Diagnostic / Negative, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0 Precision (class: diagnostic negative) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Diagnostic / Negative, precision |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0 Recall (class: diagnostic negative) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Diagnostic / Negative, recall |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.86 F1 (class: diagnostic positive) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Diagnostic / Positive, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 1 Precision (class: diagnostic positive) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Diagnostic / Positive, precision |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.75 Recall (class: diagnostic positive) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Diagnostic / Positive, recall |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.67 F1 (class: functional dominant negative) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Dominant Negative, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 1 Precision (class: functional dominant negative) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Dominant Negative, precision |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.5 Recall (class: functional dominant negative) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Dominant Negative, recall |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.57 Micro F1 (evidence type: functional) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Figure 1c, functional row, alone column |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.67 F1 (class: functional gain of function) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Gain of Function, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.75 Precision (class: functional gain of function) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Gain of Function, precision |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.6 Recall (class: functional gain of function) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Gain of Function, recall |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.55 F1 (class: functional loss of function) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Loss of Function, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.6 Precision (class: functional loss of function) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Loss of Function, precision |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.5 Recall (class: functional loss of function) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Loss of Function, recall |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0 F1 (class: functional unaltered function) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Unaltered Function, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0 Precision (class: functional unaltered function) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Unaltered Function, precision |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0 Recall (class: functional unaltered function) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Functional / Unaltered Function, recall |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.46 Micro F1 unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Fig1c Micro F1; Section 3 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.2 Micro F1 (evidence type: oncogenic) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Figure 1c, oncogenic row, alone column |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.2 F1 (class: oncogenic oncogenicity) unitless · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Oncogenic / Oncogenicity, f1 |
|---|
| Configuration: GPT-5 2025-08-07 alone, CIViC March 2026 | Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026 | 0.25 Precision (class: oncogenic oncogenicity) fraction · higher Uncertainty: Not reported by the source: not reported for this endpoint Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCIViC alone retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 2, Oncogenic / Oncogenicity, precision |
|---|