rewire.itbenchmarks
Protocol

MFASS: matched GENCODE 44 canonical annotation

8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.

4 evaluations · 16 results

Overview

8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

MFASS matched canonical annotation: Precision at 100

Precision at 100 (dimensionless) · Higher values are better.

MFASS: matched GENCODE 44 canonical annotation · MFASS v2 test: matched canonical annotation coverage

Evidence origin: Rewire evaluation.

MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.*.metrics.precision_at_capacity
  • 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.
  • Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.
  • Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.
  • Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.
  • Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.
Comparison details and limitations

8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.

Automated source review: 2026-09-25. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Showing 4 of 4 matching rows.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Published Rewire evaluations
4

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Regularised classifier on simple permitted features, or protocol's conventional reference

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV · Model evaluation matrix · Source table · Release and checksums

Coverage is derived from release 2026-09-25-d40cee0abe73. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

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.

10 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-25-d40cee0abe73
Property and statementOriginal source and locationReview and provenance
Relationship: evaluates task
catalog-task-mfass-splice
Individual claims
MFASS matched canonical annotation v1: exclusion-verification.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 4be7a98e2553fa2378c29625b13eb3e8ac2e58fb
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:evaluates_task:catalog-task-mfass-splice

Claim: rewire-mfass-matched-v1-protocol-evaluates-task-catalog-task-mfass-splice

Source artifact SHA-256: 5d2099db4cf6f01432fd88c7db949da89ab9917940705fd0eaa1fb7c9354d46a

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

Inspected artifact

Relationship: evaluates task
catalog-task-mfass-splice
Individual claims
MFASS matched canonical annotation v1: manifest-v1.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:evaluates_task:catalog-task-mfass-splice

Claim: rewire-mfass-matched-v1-protocol-evaluates-task-catalog-task-mfass-splice

Source artifact SHA-256: 3fce70dd0bd96cb92d9d0e41287f31e62ddc4ecb8d188615093a873e952433e8

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

Inspected artifact

Relationship: evaluates task
catalog-task-mfass-splice
Individual claims
MFASS matched canonical annotation v1: provenance.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:evaluates_task:catalog-task-mfass-splice

Claim: rewire-mfass-matched-v1-protocol-evaluates-task-catalog-task-mfass-splice

Source artifact SHA-256: 6304e9625e793f24cccdc2669d092e6cdcc7a508a7f789967e726816fffde062

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

Inspected artifact

Relationship: evaluates task
catalog-task-mfass-splice
Individual claims
MFASS matched canonical annotation v1: report.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:evaluates_task:catalog-task-mfass-splice

Claim: rewire-mfass-matched-v1-protocol-evaluates-task-catalog-task-mfass-splice

Source artifact SHA-256: 259eb542313914b9114c21b62891f022c0ec0d9e3337196b8d7b2c6d5ae54ef3

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

Inspected artifact

Relationship: evaluates task
catalog-task-mfass-splice
Individual claims
MFASS matched canonical annotation v1: verification.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:evaluates_task:catalog-task-mfass-splice

Claim: rewire-mfass-matched-v1-protocol-evaluates-task-catalog-task-mfass-splice

Source artifact SHA-256: 13356c3f1bd7055b11cc0ab1b2b86a7ee586c51d0c984fad6e39ce8948d662fa

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

Inspected artifact

Relationship: part of
rewire-mfass-v2
Individual claims
MFASS matched canonical annotation v1: exclusion-verification.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 4be7a98e2553fa2378c29625b13eb3e8ac2e58fb
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:part_of:rewire-mfass-v2

Claim: rewire-mfass-matched-v1-protocol-part-of-rewire-mfass-v2

Source artifact SHA-256: 5d2099db4cf6f01432fd88c7db949da89ab9917940705fd0eaa1fb7c9354d46a

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

Inspected artifact

Relationship: part of
rewire-mfass-v2
Individual claims
MFASS matched canonical annotation v1: manifest-v1.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:part_of:rewire-mfass-v2

Claim: rewire-mfass-matched-v1-protocol-part-of-rewire-mfass-v2

Source artifact SHA-256: 3fce70dd0bd96cb92d9d0e41287f31e62ddc4ecb8d188615093a873e952433e8

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

Inspected artifact

Relationship: part of
rewire-mfass-v2
Individual claims
MFASS matched canonical annotation v1: provenance.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:part_of:rewire-mfass-v2

Claim: rewire-mfass-matched-v1-protocol-part-of-rewire-mfass-v2

Source artifact SHA-256: 6304e9625e793f24cccdc2669d092e6cdcc7a508a7f789967e726816fffde062

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

Inspected artifact

Relationship: part of
rewire-mfass-v2
Individual claims
MFASS matched canonical annotation v1: report.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:part_of:rewire-mfass-v2

Claim: rewire-mfass-matched-v1-protocol-part-of-rewire-mfass-v2

Source artifact SHA-256: 259eb542313914b9114c21b62891f022c0ec0d9e3337196b8d7b2c6d5ae54ef3

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

Inspected artifact

Relationship: part of
rewire-mfass-v2
Individual claims
MFASS matched canonical annotation v1: verification.json

Original source ↗

manifest-v1.json: study and conditions

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 093fd1ae198c80ce34408d84d6543bca4fc538f2
Retrieved: 2026-09-25T11:24:56Z

source checked

automated execution evidence review · 2026-09-25T11:24:56Z

Audit details

Computational source, coverage and metric checks only; not independent human review or published-score reproduction.

Field: links:part_of:rewire-mfass-v2

Claim: rewire-mfass-matched-v1-protocol-part-of-rewire-mfass-v2

Source artifact SHA-256: 13356c3f1bd7055b11cc0ab1b2b86a7ee586c51d0c984fad6e39ce8948d662fa

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

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-25-d40cee0abe73 · Record review: source checked

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

Stable ID: rewire-mfass-matched-v1-protocol

areas
dna-genomes
version
matched-annotation-v1
source locator
manifest-v1.json; report.json
limitations
8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.; Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.; Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.; Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.
reproduction url
https://github.com/rewire-bio/rewire-benchmarks/blob/093fd1ae198c80ce34408d84d6543bca4fc538f2/benchmarks/mfass/results/matched-annotation-v1/README.md
comparison panels
id: rewire-mfass-matched-v1-precision-at-capacity; title: MFASS matched canonical annotation: Precision at 100; protocol id: rewire-mfass-matched-v1-protocol; dataset id: rewire-mfass-matched-v1-dataset; metric: Precision at 100; unit: dimensionless; direction: higher; result ids: rewire-mfass-matched-v1-result-s0-precision-at-capacity; rewire-mfass-matched-v1-result-s1-precision-at-capacity; rewire-mfass-matched-v1-result-p0-precision-at-capacity; rewire-mfass-matched-v1-result-p1-precision-at-capacity; source ids: rewire-mfass-matched-v1-source-report; rewire-mfass-matched-v1-source-manifest-v1; rewire-mfass-matched-v1-source-verification; rewire-mfass-matched-v1-source-provenance; rewire-mfass-matched-v1-source-exclusion-verification; source locator: report.json: conditions.*.metrics.precision_at_capacity; context: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; caveats: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.; Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.; Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.; Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.; review: method: automated_source_review; date: 2026-09-25; id: rewire-mfass-matched-v1-recall-at-capacity; title: MFASS matched canonical annotation: Recall at 100; protocol id: rewire-mfass-matched-v1-protocol; dataset id: rewire-mfass-matched-v1-dataset; metric: Recall at 100; unit: dimensionless; direction: higher; result ids: rewire-mfass-matched-v1-result-s0-recall-at-capacity; rewire-mfass-matched-v1-result-s1-recall-at-capacity; rewire-mfass-matched-v1-result-p0-recall-at-capacity; rewire-mfass-matched-v1-result-p1-recall-at-capacity; source ids: rewire-mfass-matched-v1-source-report; rewire-mfass-matched-v1-source-manifest-v1; rewire-mfass-matched-v1-source-verification; rewire-mfass-matched-v1-source-provenance; rewire-mfass-matched-v1-source-exclusion-verification; source locator: report.json: conditions.*.metrics.recall_at_capacity; context: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; caveats: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.; Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.; Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.; Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.; review: method: automated_source_review; date: 2026-09-25; id: rewire-mfass-matched-v1-average-precision-sklearn; title: MFASS matched canonical annotation: Average precision; protocol id: rewire-mfass-matched-v1-protocol; dataset id: rewire-mfass-matched-v1-dataset; metric: Average precision; unit: dimensionless; direction: higher; result ids: rewire-mfass-matched-v1-result-s0-average-precision-sklearn; rewire-mfass-matched-v1-result-s1-average-precision-sklearn; rewire-mfass-matched-v1-result-p0-average-precision-sklearn; rewire-mfass-matched-v1-result-p1-average-precision-sklearn; source ids: rewire-mfass-matched-v1-source-report; rewire-mfass-matched-v1-source-manifest-v1; rewire-mfass-matched-v1-source-verification; rewire-mfass-matched-v1-source-provenance; rewire-mfass-matched-v1-source-exclusion-verification; source locator: report.json: conditions.*.metrics.average_precision_sklearn; context: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; caveats: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.; Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.; Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.; Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.; review: method: automated_source_review; date: 2026-09-25; id: rewire-mfass-matched-v1-auroc; title: MFASS matched canonical annotation: AUROC; protocol id: rewire-mfass-matched-v1-protocol; dataset id: rewire-mfass-matched-v1-dataset; metric: AUROC; unit: dimensionless; direction: higher; result ids: rewire-mfass-matched-v1-result-s0-auroc; rewire-mfass-matched-v1-result-s1-auroc; rewire-mfass-matched-v1-result-p0-auroc; rewire-mfass-matched-v1-result-p1-auroc; source ids: rewire-mfass-matched-v1-source-report; rewire-mfass-matched-v1-source-manifest-v1; rewire-mfass-matched-v1-source-verification; rewire-mfass-matched-v1-source-provenance; rewire-mfass-matched-v1-source-exclusion-verification; source locator: report.json: conditions.*.metrics.auroc; context: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; caveats: 8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.; Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.; Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.; Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.; Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.; review: method: automated_source_review; date: 2026-09-25
Related records

Suggest a correction