Configuration

UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)

Configuration as run in the cited comparison.

Overview

Configuration as run in the cited comparison.

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

Evaluations and results

4 evaluations · 24 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Source checking is not independent reproduction. Release 2026-10-09-ba02f2f4a36e.

Use this model

How it works, versions and access

Strengths, limitations and unresolved questions

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 2026-10-09-ba02f2f4a36e
Property and statement	Original source and location	Review and provenance

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

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-09-ba02f2f4a36e · Record review: source checked

2 source records and release history

A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing · Original source · Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Wang et al. 2026, Data file S2 (model scores and summary statistics) · Original source · ady9432_data_file_s2.xlsx inside sciadv.ady9432_data_files_s1_and_s2.zip, PMC open-access copy PMC13353424.1

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: ctdnafrag-20261009-config-wang2026-unite-xgb-sd

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: SD
foundation model eligible: false
source locator: Data file S2 sheet STATS_xgb_x1-x6 column 'feat'; Methods P49
missing metadata: version: reason: unreported; note: No UNITE release or code commit is printed for these cross-validation models
parameters: Features: SD of fragment length counts across 5 Mb bins (SD). XGBoost with nested cross-validation (StratifiedGroupKFold, randomized grid search); keras v3.3.3 and scikit-learn v1.4.2.

Related records

Suggest a correction

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.785 accuracy fraction · higher Uncertainty: 95% CI 0.779050561231348 to 0.792040042344401. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 19 (feat 'SD', ichorcna_strat '[0, 0.03]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.907 auprc unitless · higher Uncertainty: 95% CI 0.900693647308519 to 0.912169612364319. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 15 (feat 'SD', ichorcna_strat '[0, 0.03]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.857 auroc unitless · higher Uncertainty: 95% CI 0.850185456690006 to 0.863774286981914. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 14 (feat 'SD', ichorcna_strat '[0, 0.03]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.826 f1-score fraction · higher Uncertainty: 95% CI 0.820378994382105 to 0.831384716497253. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 18 (feat 'SD', ichorcna_strat '[0, 0.03]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.818 recall fraction · higher Uncertainty: 95% CI 0.810412057218049 to 0.825496127733135. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 16 (feat 'SD', ichorcna_strat '[0, 0.03]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.732 specificity fraction · higher Uncertainty: 95% CI 0.721807366816971 to 0.742977190391783. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 17 (feat 'SD', ichorcna_strat '[0, 0.03]', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.838 accuracy fraction · higher Uncertainty: 95% CI 0.830613812851873 to 0.845857163657542. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 55 (feat 'SD', ichorcna_strat '(0.03, 0.1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.851 auprc unitless · higher Uncertainty: 95% CI 0.841009275483192 to 0.862012540007235. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 51 (feat 'SD', ichorcna_strat '(0.03, 0.1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.881 auroc unitless · higher Uncertainty: 95% CI 0.873087006282873 to 0.889265304165855. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 50 (feat 'SD', ichorcna_strat '(0.03, 0.1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.753 f1-score fraction · higher Uncertainty: 95% CI 0.738320485867839 to 0.766198715524939. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 54 (feat 'SD', ichorcna_strat '(0.03, 0.1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.695 recall fraction · higher Uncertainty: 95% CI 0.675974185333077 to 0.713634347524114. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 52 (feat 'SD', ichorcna_strat '(0.03, 0.1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.918 specificity fraction · higher Uncertainty: 95% CI 0.908511768515578 to 0.92732942166001. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 53 (feat 'SD', ichorcna_strat '(0.03, 0.1]', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.823 accuracy fraction · higher Uncertainty: 95% CI 0.818436854531976 to 0.827931097090528. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 127 (feat 'SD', ichorcna_strat 'all', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.958 auprc unitless · higher Uncertainty: 95% CI 0.95550939637201 to 0.960253579464376. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 123 (feat 'SD', ichorcna_strat 'all', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.888 auroc unitless · higher Uncertainty: 95% CI 0.883469579720277 to 0.892752637786812. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 122 (feat 'SD', ichorcna_strat 'all', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.878 f1-score fraction · higher Uncertainty: 95% CI 0.874094773461295 to 0.881225655016333. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 126 (feat 'SD', ichorcna_strat 'all', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.86 recall fraction · higher Uncertainty: 95% CI 0.853246847007509 to 0.867839214961162. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 124 (feat 'SD', ichorcna_strat 'all', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.719 specificity fraction · higher Uncertainty: 95% CI 0.703788356631913 to 0.736204834945551. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 125 (feat 'SD', ichorcna_strat 'all', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.93 accuracy fraction · higher Uncertainty: 95% CI 0.924268762879058 to 0.935073189743791. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 91 (feat 'SD', ichorcna_strat '(0.1, 1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.967 auprc unitless · higher Uncertainty: 95% CI 0.96201721939972 to 0.970837933606336. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 87 (feat 'SD', ichorcna_strat '(0.1, 1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.97 auroc unitless · higher Uncertainty: 95% CI 0.965356995466772 to 0.974346713364885. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 86 (feat 'SD', ichorcna_strat '(0.1, 1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.902 f1-score fraction · higher Uncertainty: 95% CI 0.893221401906091 to 0.90994869673652. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 90 (feat 'SD', ichorcna_strat '(0.1, 1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.864 recall fraction · higher Uncertainty: 95% CI 0.853111259234702 to 0.876139072637228. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 88 (feat 'SD', ichorcna_strat '(0.1, 1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, SD of fragment length counts across 5 Mb bins (SD) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.97 specificity fraction · higher Uncertainty: 95% CI 0.963659665151621 to 0.97590520511239. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 89 (feat 'SD', ichorcna_strat '(0.1, 1]', .metric 'Specificity'), column D 'mean'