rewirebio.iobenchmarks
Evaluation

Ladon + clinical covariates, held-out trials OS hazard ratio

Developer-reported evaluation transcribed from the pinned Ladon technical report; not reproduced.

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: Ladon + clinical covariates, summed standardised risk scores (held-out trials)Protocol: Held-out trials, OS hazard ratio of higher- against lower-risk half, geometric mean over six trials
Dataset subset: Six held-out trials with overall survival
2.15 Hazard ratio (hazard ratio, higher-risk half against lower-risk half at the median predicted risk, overall survival, Cox stratified by treatment arm, Efron ties, full follow-up; equal-trial geometric mean over six trials)
unitless · higher

Uncertainty: Not reported by the source: Per-trial dots and a bar only; no interval is printed.

Coverage: 6/6 trials scored (IMbrave150 uses Ladon alone in the combined predictor.)

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

Ladon + clinical covariates, held-out trials OS hazard ratio

ladon-20261115-protocol-trials-os-hazard-ratio

Aggregation: Not reported

Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF) · Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS 2.15'

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

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-c8bea25e5abb · 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.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

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.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

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.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

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.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

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.

Evaluation procedure

Held-out trials, OS hazard ratio of higher- against lower-risk half, geometric mean over six trials

Configuration
Ladon + clinical covariates, summed standardised risk scores (held-out trials)
Protocol
Held-out trials, OS hazard ratio of higher- against lower-risk half, geometric mean over six trials
Dataset subset
Six held-out trials with overall survival
origin
Author-reported evaluation
configuration
Zenodo 10.5281/zenodo.24157116, PDF dated 12 November 2026
adaptation
Sum of standardised Ladon and clinical-covariate risk scores (Ladon alone in IMbrave150)
aggregation
Equal-trial geometric mean over 6 trials
budget
Not reported
dataset version
Not reported
inputs
Pretreatment bulk RNA-seq (or clinical text for the clinical baseline)
metric implementation
Median split of predicted risk; unpenalised Cox with binary group indicator stratified by arm, Efron ties
population
6 trials with OS readouts
protocol id
ladon-20261115-protocol-trials-os-hazard-ratio
split
Held-out trial; predictor fitted on TCGA and the other trials

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

Reproduction

Split
Held-out trial; predictor fitted on TCGA and the other trials
Adaptation
Sum of standardised Ladon and clinical-covariate risk scores (Ladon alone in IMbrave150)
Scoring implementation
Median split of predicted risk; unpenalised Cox with binary group indicator stratified by arm, Efron ties

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.

24 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
Comparison: adaptation
Sum of standardised Ladon and clinical-covariate risk scores (Ladon alone in IMbrave150)
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: aggregation
Equal-trial geometric mean over 6 trials
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: budget
Not reported
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: dataset version
Not reported
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: inputs
Pretreatment bulk RNA-seq (or clinical text for the clinical baseline)
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: metric implementation
Median split of predicted risk; unpenalised Cox with binary group indicator stratified by arm, Efron ties
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.metric_implementation

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: population
6 trials with OS readouts
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: protocol id
ladon-20261115-protocol-trials-os-hazard-ratio
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.protocol_id

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Comparison: split
Held-out trial; predictor fitted on TCGA and the other trials
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.split

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

Coverage: eligible
6
Context-only references
Ladon: An RNA Foundation Model for Predicting Patient Outcomes (Zenodo PDF)

Original source ↗

Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'

Version: Zenodo record 24157116 (version DOI 10.5281/zenodo.24157116; concept DOI 10.5281/zenodo.24157115), file Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf, 47 pages, dated 12 November 2026
Retrieved: 2026-11-15T20:29:10Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.coverage.eligible

Source artifact SHA-256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c

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

How to read the evidence

Sources and history

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

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: ladon-20261115-eval-fig3-ladon-plus-clinical-covariates-os

areas
rna-transcriptomes
contexts
clinical_research
comparison
adaptation: Sum of standardised Ladon and clinical-covariate risk scores (Ladon alone in IMbrave150); aggregation: Equal-trial geometric mean over 6 trials; budget: Not reported; dataset version: Not reported; inputs: Pretreatment bulk RNA-seq (or clinical text for the clinical baseline); metric implementation: Median split of predicted risk; unpenalised Cox with binary group indicator stratified by arm, Efron ties; population: 6 trials with OS readouts; protocol id: ladon-20261115-protocol-trials-os-hazard-ratio; split: Held-out trial; predictor fitted on TCGA and the other trials
coverage
eligible: 6; note: IMbrave150 uses Ladon alone in the combined predictor.; scored: 6; unit: trials
limitations
Developer-reported by Blank Bio, which built Ladon and ran every comparator; not reproduced by Rewire.
origin
author_reported
protocol
ladon-20261115-protocol-trials-os-hazard-ratio
retrospective
true
review
artifact sha256: 64edf7c3c956c50a65aa01a0dcaa13f0cfef28ab4373ecfd50c431e67143893c; method: pdf-text-parse; source-hash-verification; automated-source-review; method note: Independent review pass. All 216 non-result records were checked by review/check_claim_quotes.py, written for this pass, which looks for every quoted phrase and every number a record states in the text of the sources that record cites: the pinned PDF's pdftotext -layout text layer, and for records citing them the announcement page and the Figure 6 page, whose embedded DATA object is searched as text rather than stripped as script. 182 quoted phrases and 1,136 numbers; three were not found by search and each was then read by hand and accepted, with the reason recorded in review/claim-quote-check.tsv (a sum the field itself labels as the extractor's, a row label the text layer breaks across two lines, and a locator joining a panel's two printed header lines with a comma). Pages 6 to 10, 12, 13, 15 to 17, 19, 20, 24 to 28, 33, 35 and 39 were read in full, and these were checked against the records in particular: the trial, endpoint and patient counts of pages 12, 13 and 15 against the dataset and dataset-subset records; the fitting procedures of pages 12 and 13 against each configuration; the geometric-mean and size-weighted aggregations of page 13 against the Figure 3 and Figure 5 protocols; the reimplementation sentence on page 39 against the CIBERSORT and DWLS method records; and the bootstrap statements on pages 28 and 39 against the stored uncertainty methods and resample counts. Pages the records cite but that were not read line by line (pages 11, 14, 18, 22, 29, 38 and 40 to 43) are covered by the quote and number check alone.; note: Re-read at the locator this record names; it matched.; retrieval url: https://zenodo.org/api/records/24157116/files/Ladon-An-RNA-Foundation-Model-for-Predicting-Patient-Outcomes.pdf/content; reviewed at: 2026-11-15T23:30:00Z; reviewer: claude; reviewer note: Claude review agent, independent of the extractor; no human review claimed. Transcription was checked against the pinned sources, which is not reproduction: nothing was rerun and no value was recomputed.
source locator
Figure 3 (page 7), row 'Ladon + clinical covariates', label 'OS'
version
Zenodo 10.5281/zenodo.24157116, PDF dated 12 November 2026
Related records

Suggest a correction