Result

AUROC difference (Gene-level features plus correlation edge minus gene-level features only (gene-level logistic regression); cross-validated AUROC over perturbation-gene pairs, 5-fold GroupKFold by perturbation) of Gene-level logistic regression plus correlation edge (Kendiukhov 2026) on Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations (Kendiukhov 2026)

−0.002 AUROC difference (Gene-level features plus correlation edge minus gene-level features only (gene-level logistic regression); cross-validated AUROC over perturbation-gene pairs, 5-fold GroupKFold by perturbation)

Methods

Tested configuration: Gene-level logistic regression plus correlation edge (Kendiukhov 2026)
Protocol: Gene-level logistic regression under 5-fold GroupKFold by perturbation (Kendiukhov 2026)
Dataset subset: Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations (Kendiukhov 2026)
Procedure: Gene-level logistic regression under 5-fold GroupKFold by perturbation (Kendiukhov 2026)
Evaluation: Gene-level logistic regression plus correlation edge on Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations
Coverage: Not reported scored / Not reported eligible
Uncertainty: 95% CI -0.005 to 0.000. Methods 'Statistical framework': bootstrap CIs use 200 iterations with perturbation-level resampling unless otherwise noted; Fig. 4B caption: 'Bootstrap ∆AUROC distribution (n = 100)'
Evidence: Author-reported evaluation · source checkedSystematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction (Kendiukhov 2026, BMC Genomics 27:634) · Page 8, 'No incremental pairwise value on the perturbation-target prediction task', paragraph 1, sentence 2: 'adding correlation yields ∆AUROC = −0.002 [−0.005, 0.000]'

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: 5-fold GroupKFold by perturbation
Adaptation: Foundation-model attention read out zero-shot; correlation and gene-level statistics computed from the same control cells; logistic regression fitted under GroupKFold
Scoring implementation: Cross-validated AUROC over perturbation-gene pairs

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance
Reported result −0.002 Individual claims	Systematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction (Kendiukhov 2026, BMC Genomics 27:634) Original source ↗ Page 8, 'No incremental pairwise value on the perturbation-target prediction task', paragraph 1, sentence 2: 'adding correlation yields ∆AUROC = −0.002 [−0.005, 0.000]' Version: Version of record, BMC Genomics 27:634, published 2026-07-22 (received 2026-03-10, accepted 2026-05-14) Retrieved: 2026-10-14T12:01:07Z	source checked ["source-hash-verification","pdf-text-parse","independent-cell-check"] · 2026-10-14 author reported Audit details Extraction: Hand transcription from the article text; extract/extract_delta.py asserts that the quoted fragment, which contains the printed value, occurs on the stated page of the pdftotext output of the pinned PDF. Independent review 2026-10-14: matched. Field: `attributes.printed_value` Source artifact SHA-256: `4c1699cb964ae588117a6737f5e9e189eb9a5ef5ff78568d2a99e7a13d6608fe` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `4c1699cb964ae588117a6737f5e9e189eb9a5ef5ff78568d2a99e7a13d6608fe` Extraction artifact

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Systematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction (Kendiukhov 2026, BMC Genomics 27:634) · Original source · Version of record, BMC Genomics 27:634, published 2026-07-22 (received 2026-03-10, accepted 2026-05-14)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-kendiukhov2026-result-incremental-value-lr-k562-crispri-280-gene-level-lr-plus-correlation-auroc-difference

metric: auroc-difference
metric direction: higher
unit: unitless
printed value: −0.002
numeric value: -0.002
metric qualifier: Gene-level features plus correlation edge minus gene-level features only (gene-level logistic regression); cross-validated AUROC over perturbation-gene pairs, 5-fold GroupKFold by perturbation
source locator: Page 8, 'No incremental pairwise value on the perturbation-target prediction task', paragraph 1, sentence 2: 'adding correlation yields ∆AUROC = −0.002 [−0.005, 0.000]'
review: method: source-hash-verification; pdf-text-parse; independent-cell-check; method note: Archived PDF hashes to the pinned SHA-256 (a fresh download returned a bot-check page). Each value, its sign, interval, sentence, page, perturbation set, configuration, reference system and protocol re-read by hand in the pdftotext layer; the 559,720 K562 observations equal 280 x 1,999, confirming the 280-perturbation subset.; reviewer: claude; reviewer note: Claude (Opus 5.5) research agent, independent of the extractor; no human review claimed; date: 2026-10-14; artifact sha256: 4c1699cb964ae588117a6737f5e9e189eb9a5ef5ff78568d2a99e7a13d6608fe; retrieval url: https://bmcgenomics.biomedcentral.com/counter/pdf/10.1186/s12864-026-12965-8.pdf; note: Extraction: Hand transcription from the article text; extract/extract_delta.py asserts that the quoted fragment, which contains the printed value, occurs on the stated page of the pdftotext output of the pinned PDF. Independent review 2026-10-14: matched.
uncertainty: type: confidence_interval; lower: -0.005; upper: 0.000; level: 0.95; method: bootstrap; printed: [−0.005, 0.000]; note: Methods 'Statistical framework': bootstrap CIs use 200 iterations with perturbation-level resampling unless otherwise noted; Fig. 4B caption: 'Bootstrap ∆AUROC distribution (n = 100)'

Related records

evaluation: Gene-level logistic regression plus correlation edge on Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations

Suggest a correction