AUROC (LOF against FUNC and INT, all SNVs) of SpliceAI precomputed masked score from the CADD v1.7 annotations on BRCA1 saturation genome editing SNVs, all SNVs (evo2-cloud-operations W1)
0.694 AUROC (LOF against FUNC and INT, all SNVs)
Methods
- Tested configuration
- SpliceAI precomputed masked score from the CADD v1.7 annotations
- Protocol
- Zero-shot BRCA1 loss-of-function classification, all SNVs (evo2-cloud-operations W1)
- Dataset subset
- BRCA1 saturation genome editing SNVs, all SNVs (evo2-cloud-operations W1)
- Procedure
- LOF against FUNC and INT; AUROC of the score oriented so that higher means loss of function
- Evaluation
- SpliceAI on BRCA1 all SNVs
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- 95% CI 0.6649186773849238 to 0.7233661186966525
- Evidence
- Rewire evaluation · source checkedevo2-cloud-operations amendment 7: current predictors results.json · evidence/current-predictors/results.json, JSON pointer /main/all/auroc/spliceai/auroc
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
- none; every variant of the subset is scored
- Adaptation
- zero-shot; no fitting on these variants
- Scoring implementation
- src/study/analysis.py; the recorded run used revision e93491a (evidence/runs/recorded-b75c67aa/provenance.json), an ancestor of the pinned commit
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 0.6939551414741492 Individual claims | evo2-cloud-operations amendment 7: current predictors results.json evidence/current-predictors/results.json, JSON pointer /main/all/auroc/spliceai/auroc Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905 | source checked ["execution-evidence-review","source-hash-verification"] · 2026-11-21 rewire run Audit detailsComputed by Rewire from a lookup score or from committed Evo 2 scores; no run receipt covers this value. Field: Source artifact SHA-256: Hash scope: complete bytes of the file at the pinned commit Extraction artifact SHA-256: |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- evo2-cloud-operations amendment 7: current predictors results.json · Original source · f8ae11c9a1c45505487c978b4cb7e064c4e59905
Technical metadata and extraction receipts
Stable ID: rewire-local-20261121-evo2ops-result-spliceai-brca1-all-auroc
- areas
- dna-genomes
- printed value
- 0.6939551414741492
- numeric value
- 0.6939551414741492
- metric
- auroc
- metric direction
- higher
- unit
- unitless
- metric qualifier
- LOF against FUNC and INT, all SNVs
- uncertainty
- type: confidence_interval; lower: 0.6649186773849238; upper: 0.7233661186966525; level: 0.95; method: bootstrap; resamples: 2000; scope: bootstrap over positions, the three SNVs at a position kept together; source column: JSON pointer /main/all/auroc/spliceai/ci95
- source locator
- evidence/current-predictors/results.json, JSON pointer /main/all/auroc/spliceai/auroc
- review
- method: execution-evidence-review; source-hash-verification; reviewer: claude; date: 2026-11-21; artifact sha256: 403437941f5a0e08b3730fa7bbfcba0b8e616b0e87b2f8e3f227b2f86a342318; retrieval url: https://raw.githubusercontent.com/rewire-bio/evo2-cloud-operations/f8ae11c9a1c45505487c978b4cb7e064c4e59905/evidence/current-predictors/results.json; method note: Value read by build_batch.py as the literal JSON number token at the pointer in the pinned file, then re-read from the same bytes and compared; file hash recomputed from a fresh download of the raw URL; reviewer note: Claude agent, automated. The same agent wrote the generator and ran its re-read check; no independent second pass and no human review; note: Computed by Rewire from a lookup score or from committed Evo 2 scores; no run receipt covers this value.
Related records
- evaluation: SpliceAI on BRCA1 all SNVs