rewire.itbenchmarks
Evaluation

sctab uncertainty known-type error discrimination

Author-reported evaluation; no new execution.

Research readiness

These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.

Release 2026-10-06-161b59a1d02c · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • metric replay: verification is missing

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • metric replay: verification is missing
  • annotations: verification is missing
  • dependence: verification is missing

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • recipe pinned: verification is missing
  • resource estimate: verification is missing

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • independent validation: verification is missing
  • overlap checked: verification is missing

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Read reviewed discrepancy investigations

Evaluation results

1 evaluation · 1 result. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: scTab — scTab Table 1Protocol: scTab deep-ensemble uncertainty ROC-AUC: known-type correct vs. incorrect (Group 1 vs. Group 2)
Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts
0.891 roc-auc
fraction · higher

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

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

sctab uncertainty known-type error discrimination

Not reported

Aggregation: Not reported

scTab: Scaling cross-tissue single-cell annotation models · Methods, "Uncertainty quantification for scTab model": "Group 1 and Group 2 can even be separated with an ROC-AUC score of 0.891"

Source checking is not independent reproduction. Release 2026-10-06-161b59a1d02c.

Evaluation procedure

Not reported

Configuration
scTab — scTab Table 1
Protocol
scTab deep-ensemble uncertainty ROC-AUC: known-type correct vs. incorrect (Group 1 vs. Group 2)
Dataset
scTab processed CELLxGENE 2023-05-15 donor holdouts
origin
Author-reported evaluation
configuration
Not reported
protocol id
ucc-research-protocol-sctab-uncertainty-error
dataset version
CELLxGENE 2023-05-15 scTab processed corpus
split
donor-based; not whole-study or whole-platform holdout
population
Group 1 (correct, known-type) vs. Group 2 (incorrect, known-type); exact group sizes not stated in the retrieved main text
inputs
Not independently restated in this subsection; the configuration link reflects this subsection's own heading, "Uncertainty quantification for scTab model," not a repeated statement of training settings (e.g., data augmentation) for the ensemble members used here.
adaptation
Deep ensemble of 5 independently trained scTab models; predicted probabilities are averaged across the ensemble first, then uncertainty = 1 minus the maximum of that averaged probability vector.
aggregation
metric-specific; inspect result

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
donor-based; not whole-study or whole-platform holdout
Adaptation
Deep ensemble of 5 independently trained scTab models; predicted probabilities are averaged across the ensemble first, then uncertainty = 1 minus the maximum of that averaged probability vector.
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.

14 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-06-161b59a1d02c
Property and statementOriginal source and locationReview and provenance
attributes.comparison.adaptation
Deep ensemble of 5 independently trained scTab models; predicted probabilities are averaged across the ensemble first, then uncertainty = 1 minus the maximum of that averaged probability vector.
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.comparison.aggregation
metric-specific; inspect result
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.comparison.dataset_version
CELLxGENE 2023-05-15 scTab processed corpus
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.comparison.inputs
Not independently restated in this subsection; the configuration link reflects this subsection's own heading, "Uncertainty quantification for scTab model," not a repeated statement of training settings (e.g., data augmentation) for the ensemble members used here.
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.comparison.population
Group 1 (correct, known-type) vs. Group 2 (incorrect, known-type); exact group sizes not stated in the retrieved main text
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.comparison.protocol_id
ucc-research-protocol-sctab-uncertainty-error
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.protocol_id

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.comparison.split
donor-based; not whole-study or whole-platform holdout
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.split

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.ensemble_size
5
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.ensemble_size

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.origin
author_reported
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.origin

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

description
Author-reported evaluation; no new execution.
Context-only references
scTab: Scaling cross-tissue single-cell annotation models

Original source ↗

No field-specific location recorded

Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30
Retrieved: 2026-09-30T21:23:28Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: description

Source artifact SHA-256: Not recorded

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-10-06-161b59a1d02c · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: ucc-research-eval-sctab-uncertainty-error

origin
author_reported
review
method: automated_source_review; actor: Claude Sonnet cell-type-annotation-transfer evidence-research worker; reviewed at: 2026-10-06T22:08:45Z; note: Source-backed primary-text transcription and independent re-verification against the already-catalogued scTab source (byte-identical SHA-256 re-check), continuing the bounded 2026-10-06 research dossier (docs/omics/evidence-research/cell-type-annotation-transfer-2026-10-06.md). Revised after an independent review found the averaging order, ensemble terminology and training-setting link needed correction; see below. No new model execution, independent experimental replication, or qualified human scientific review.
comparison
protocol id: ucc-research-protocol-sctab-uncertainty-error; dataset version: CELLxGENE 2023-05-15 scTab processed corpus; split: donor-based; not whole-study or whole-platform holdout; population: Group 1 (correct, known-type) vs. Group 2 (incorrect, known-type); exact group sizes not stated in the retrieved main text; inputs: Not independently restated in this subsection; the configuration link reflects this subsection's own heading, "Uncertainty quantification for scTab model," not a repeated statement of training settings (e.g., data augmentation) for the ensemble members used here.; adaptation: Deep ensemble of 5 independently trained scTab models; predicted probabilities are averaged across the ensemble first, then uncertainty = 1 minus the maximum of that averaged probability vector.; aggregation: metric-specific; inspect result
ensemble size
5
Related records

Suggest a correction