Result

0.823 accuracy

wang2026-sd-tf-all accuracy (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))

Tested 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
Procedure: ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all
Evaluation: UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions
Coverage: Not reported scored / Not reported eligible
Uncertainty: 95% CI 0.818436854531976 to 0.827931097090528. Interval over the 50 outer test folds as printed in columns G and H
Evidence: Author-reported evaluation · source checkedA 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'

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split: Nested 5-fold cross-validation, 10 repeats
Adaptation: Model trained per outer fold with inner hyperparameter search
Scoring implementation: Not reported

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

2 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
Reported result 0.823184358523676 Individual claims	A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing Original source ↗ Data file S2 sheet STATS_xgb_x1-x6, row 127 (feat 'SD', ichorcna_strat 'all', .metric 'Accuracy'), column D 'mean' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML Retrieved: 2026-10-09T20:27:02Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 author reported Audit details Extracted by deterministic parse of the pinned XLSX cell XML of ady9432_data_file_s2.xlsx (extract/rawxlsx.py) with headers, strata, feature and metric labels asserted. Each row's mean is the value; ci_95_lower and ci_95_upper are the uncertainty; median, sd and the sem bounds are in source_cells. General-format cells; printed_value is the shortest round-trip decimal of the stored value. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `d28e1dbf64df93fdefd7dd239ab773088b4f27000807c81dd84b0511c64efe12` Extraction artifact
Reported result 0.823184358523676 Individual claims	Wang et al. 2026, Data file S2 (model scores and summary statistics) Original source ↗ Data file S2 sheet STATS_xgb_x1-x6, row 127 (feat 'SD', ichorcna_strat 'all', .metric 'Accuracy'), column D 'mean' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: ady9432_data_file_s2.xlsx inside sciadv.ady9432_data_files_s1_and_s2.zip, PMC open-access copy PMC13353424.1 Retrieved: 2026-10-09T20:23:13Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 author reported Audit details Extracted by deterministic parse of the pinned XLSX cell XML of ady9432_data_file_s2.xlsx (extract/rawxlsx.py) with headers, strata, feature and metric labels asserted. Each row's mean is the value; ci_95_lower and ci_95_upper are the uncertainty; median, sd and the sem bounds are in source_cells. General-format cells; printed_value is the shortest round-trip decimal of the stored value. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `d28e1dbf64df93fdefd7dd239ab773088b4f27000807c81dd84b0511c64efe12` Hash scope: artifact_sha256 is the zip as served; the member ady9432_data_file_s2.xlsx has SHA-256 32ae4ff3b7e1c85fa8662a57b45f77330e56e475f996f6489f25e36a81de65aa Archive member: ady9432_data_file_s2.xlsx Inspected artifact Extraction artifact SHA-256: `d28e1dbf64df93fdefd7dd239ab773088b4f27000807c81dd84b0511c64efe12` Extraction artifact

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-result-wang2026-sd-tf-all-accuracy

metric: accuracy
metric qualifier: cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats)
metric direction: higher
unit: fraction
printed value: 0.823184358523676
numeric value: 0.823184358523676
source locator: Data file S2 sheet STATS_xgb_x1-x6, row 127 (feat 'SD', ichorcna_strat 'all', .metric 'Accuracy'), column D 'mean'
review: method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the data-file zip, matched its SHA-256 and the SHA-256 of member ady9432_data_file_s2.xlsx. Read the row with a separate stdlib OOXML reader written for this review (raw cell text; number format General); the extractor's scripts were not imported or run. Checked the stratum, feature and metric labels, the mean (value), the 95% CI and the median, SD and SEM cells, metric, qualifier, unit, direction, and the linked evaluation's configuration, protocol and dataset. The sheet's means and medians were recomputed from the 50 per-fold values in the matching RAW sheet.; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-09; artifact sha256: d28e1dbf64df93fdefd7dd239ab773088b4f27000807c81dd84b0511c64efe12; retrieval url: https://pmc-oa-opendata.s3.amazonaws.com/PMC13353424.1/sciadv.ady9432_data_files_s1_and_s2.zip; note: Extracted by deterministic parse of the pinned XLSX cell XML of ady9432_data_file_s2.xlsx (extract/rawxlsx.py) with headers, strata, feature and metric labels asserted. Each row's mean is the value; ci_95_lower and ci_95_upper are the uncertainty; median, sd and the sem bounds are in source_cells. General-format cells; printed_value is the shortest round-trip decimal of the stored value. Independent review 2026-10-09: value and identity match the source.
uncertainty: type: confidence_interval; lower: 0.818436854531976; upper: 0.827931097090528; level: 0.95; printed: ci_95_lower 0.818436854531976, ci_95_upper 0.827931097090528; note: Interval over the 50 outer test folds as printed in columns G and H
raw xml value: 0.823184358523676
source cells: E127 median 0.82257776043445; F127 sd 0.0175620507972114; I127 sem_lower 0.820700709481626; J127 sem_upper 0.825668007565726

Related records

evaluation: UNITE XGBoost SD of fragment length counts across 5 Mb bins (SD), all tumour fractions

Suggest a correction