Model type
Train-only gradient-boosted-tree baseline
Configuration
Corrected k-mer / position baseline
The corrected MFASS baseline combines local sequence composition, allele identity, exon position and conservation in gradient-boosted trees.
Sources
MFASS v2 run_baseline.py · run_baseline.py module documentation and recorded runner configurationHow it worksEvaluated pipeline
Schematic of the pinned MFASS configuration; this does not generalise to every member of the model family.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607eAt a glance
Biological inputs
Assay-oriented allele pairs, variant/exon positions, phyloP and phastCons annotations
Sources
MFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedureOutputs
Probability of MFASS splice disruption
Sources
MFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedureSource reviewed · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 3 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Corrected k-mer / position baseline on MFASS v2 Configuration: Corrected k-mer / position baselineProtocol: MFASS v2Dataset: MFASS v2 eligible assay cohort Assay-oriented 21 bp k-mer window, exon position, allele identity and conservation features; gradient-boosted trees trained on the MFASS training split. Rewire evaluation · Evaluation metadata: reproduced | ||
| 0.7779498064677238 auroc Unit: fraction · Direction: higher | Uncertainty: Point estimate; see paired-comparison artifacts. Coverage (scored/eligible): 8324/8324 | reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/baseline-kmer-position-v2.json :: auroc Source checking is not independent reproduction. |
| 0.28641674595892375 average_precision Unit: fraction · Direction: higher | Uncertainty: Point estimate; see paired-comparison artifacts. Coverage (scored/eligible): 8324/8324 | reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/baseline-kmer-position-v2.json :: average_precision Source checking is not independent reproduction. |
| 0.61 precision_at_100 Unit: fraction · Direction: higher | Uncertainty: Point estimate; see paired-comparison artifacts. Coverage (scored/eligible): 8324/8324 | reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/baseline-kmer-position-v2.json :: precision_at_100 Source checking is not independent reproduction. |
How it works
Evaluated procedure
Features use an assay-oriented 21-base window centred on the validated variant position. The model is trained on the fixed MFASS training split, then scores the held-out variants. The corrected orientation is part of the method identity.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607eStrengths and limitations
Strengths supported by sources
- Provides an interpretable feature-based reference for asking whether a more complex model adds value.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607e
Limitations and conditions
- It uses assay-specific labels and engineered annotation features. It is not a zero-shot baseline with the same inputs as every specialist.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607e
Profile review details
Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.
Stable record: rewire-model-baseline-kmer-position-v2Specifications
Inputs, training, access and other details
Explanatory profile: source reviewed · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Train-only gradient-boosted-tree baselineSourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Architecture / procedure | HistGradientBoostingClassifier on allele, exon-distance, conservation and 3-mer features. Corrected windows use validated assay-oriented mutant sequences.SourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Biological inputs | Assay-oriented allele pairs, variant/exon positions, phyloP and phastCons annotationsSourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Outputs | Probability of MFASS splice disruptionSourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Parameters | Not a pretrained neural parameter count; fitted tree structure is controlled by the runner configuration.SourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Training data / fitting | 19,409 MFASS train variants in split-v2; feature fitting and model training use train rows only.SourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Context limits | A 21-bp variant-centred sequence window supplies 3-mer composition; other positional and conservation features are also provided.SourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Known versions / configuration | bee9133b83f3aedaf2bbb9013f1875515845607eSourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Access | Public pinned benchmark source; no genome retrieval or pretrained weight download required.SourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
| Code licence | MIT for the Rewire runner at the reviewed revision.SourcesRewire benchmark runner licence · LICENSE; complete MIT grant |
| Weights licence | Not applicable to a pretrained model; the fitted baseline is an experiment artifact. · Not applicableSourcesMFASS v2 run_baseline.py · run_baseline.py; module documentation, main() configuration and scoring procedure |
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.
18 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Schematic of the pinned MFASS configuration; this does not generalise to every member of the model family. Individual claims | MFASS v2 pinned rewire artifacts benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607e Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash |
| Diagram steps ["Validated assay sequence","21-base window and features","Training split","Gradient-boosted trees","Held-out ranking"] Individual claims | MFASS v2 pinned rewire artifacts benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607e Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash |
| Diagram title Evaluated pipeline Individual claims | MFASS v2 pinned rewire artifacts benchmarks/mfass/src/mfass/run_baseline.py, featurise; results/baseline-kmer-position-v2.json at bee9133b83f3aedaf2bbb9013f1875515845607e Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash |
| Model type Train-only gradient-boosted-tree baseline Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure HistGradientBoostingClassifier on allele, exon-distance, conservation and 3-mer features. Corrected windows use validated assay-oriented mutant sequences. Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence Not applicable to a pretrained model; the fitted baseline is an experiment artifact. Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | inapplicable automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Assay-oriented allele pairs, variant/exon positions, phyloP and phastCons annotations Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Probability of MFASS splice disruption Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters Not a pretrained neural parameter count; fitted tree structure is controlled by the runner configuration. Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Training data / fitting 19,409 MFASS train variants in split-v2; feature fitting and model training use train rows only. Individual claims | MFASS v2 run_baseline.py run_baseline.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: source checked
3 source records and release history
- MFASS v2 pinned rewire artifacts · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- MFASS v2 run_baseline.py · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- Rewire benchmark runner licence · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
Technical metadata and extraction receipts
Stable ID: rewire-model-baseline-kmer-position-v2
- areas
- dna-genomes
- entity level
- method
- version
- bee9133b83f3aedaf2bbb9013f1875515845607e
- reported name
- Corrected k-mer / position baseline
- historical missing metadata
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: evidence-reported-rewire-run-baseline; source locator: run_baseline.py; module documentation, main() configuration and scoring procedure | run_baseline.py module documentation and recorded runner configuration; ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.