rewirebio.iobenchmarks
Protocol

Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction

AUC and sensitivity at the predefined cutoff, overall and within ichorCNA tumour-fraction strata, on the 5,996-sample independent test cohort.

1 evaluation · 11 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

1 recorded evaluation, 11 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

1 evaluation · 11 results. Different protocols are not a single leaderboard.

Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction · Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)

Sorted by AUROC (all cancers vs non-cancer) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationAUROC (all cancers vs non-cancer)AUROC (high-TF (> 5%) cancers vs non-cancer)AUROC (low-TF (< 3%) cancers vs non-cancer)AUROC (medium-TF (3-5%) cancers vs non-cancer)Recall (sensitivity, all cancers, at the predefined cutoff (98% specificity in the training cohort))Recall (sensitivity, high-TF (> 5%) cancers, at the predefined cutoff (98% specificity in the training cohort))Recall (sensitivity, low-TF (< 3%) cancers, at the predefined cutoff (98% specificity in the training cohort))Recall (sensitivity, low-TF (< 3%) stage I/II cancers, at the predefined cutoff (98% specificity in the training cohort))Recall (sensitivity, low-TF (< 3%) stage III/IV cancers, at the predefined cutoff (98% specificity in the training cohort))Recall (sensitivity, medium-TF (3-5%) cancers, at the predefined cutoff (98% specificity in the training cohort))Specificity (non-cancer controls, at the predefined cutoff (98% specificity in the training cohort))
Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Evaluation0.930.9840.910.9580.580.910.460.3910.7080.720.97
All 11 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.984 AUROC (high-TF (> 5%) cancers vs non-cancer)
unitless · higher

Uncertainty: 95% CI 0.979 to 0.989. Method not stated

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 3
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.91 AUROC (low-TF (< 3%) cancers vs non-cancer)
unitless · higher

Uncertainty: 95% CI 0.902 to 0.917. Method not stated

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 3
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.958 AUROC (medium-TF (3-5%) cancers vs non-cancer)
unitless · higher

Uncertainty: 95% CI 0.940 to 0.976. Method not stated

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 3
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.93 AUROC (all cancers vs non-cancer)
unitless · higher

Uncertainty: 95% CI 0.924 to 0.936. Method not stated

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 2
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.58 Recall (sensitivity, all cancers, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 5
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.91 Recall (sensitivity, high-TF (> 5%) cancers, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 6
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.46 Recall (sensitivity, low-TF (< 3%) cancers, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 6
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.391 Recall (sensitivity, low-TF (< 3%) stage I/II cancers, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: 95% CI 0.367 to 0.415. Method not stated

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Supplementary Table S4, row 'Test' / 'I/II', column 'Sensitivity (95% CI)'
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.708 Recall (sensitivity, low-TF (< 3%) stage III/IV cancers, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: 95% CI 0.666 to 0.748. Method not stated

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Supplementary Table S4, row 'Test' / 'III/IV', column 'Sensitivity (95% CI)'
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.72 Recall (sensitivity, medium-TF (3-5%) cancers, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 6
Configuration: Fragmentia-AI WGS, high/medium/low-TF sequential fine-tuning (final model)Protocol: Fragmentia-AI WGS paper: Independent test cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS independent test cohort (5,996 samples, 0.05x ULP-WGS)
0.97 Specificity (non-cancer controls, at the predefined cutoff (98% specificity in the training cohort))
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the independent test cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-test

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P19, sentence 5

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations
1

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-11-21-c8bea25e5abb. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

2 source records and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID ctdnalit-20261011-fragmentiawgs2026-protocol-test.

Source locator: Results P19; Table S4

Related records

Suggest a correction