Protocol

PepSpecBench MassIVE-KB-Mini test split, median SA

In-domain test on the backbone-disjoint split; median SA over spectra in the shared canonical fragment space.

Overview

An explanatory profile has not yet been reviewed for this record.

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

6 recorded evaluations, 12 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

6 evaluations · 12 results. Different protocols are not a single leaderboard.

Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA · Dataset: PepSpecBench MassIVE-KB-Mini test split

Sorted by Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) (lower is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14))	Spectral angle (median over spectra, shared canonical fragment space)
Prosit Transformer retrained on MassIVE-KB (PepSpecBench)Evaluation	0.0977 (best in column)	0.098 (best in column)
Prosit retrained on MassIVE-KB (PepSpecBench)Evaluation	0.0995	0.1
AlphaPeptDeep retrained on MassIVE-KB (PepSpecBench)Evaluation	0.129	0.129
PredFull retrained on MassIVE-KB (PepSpecBench)Evaluation	0.167	0.167
UniSpec retrained on MassIVE-KB (PepSpecBench)Evaluation	0.337	0.337
FastSpel retrained on MassIVE-KB (PepSpecBench)Evaluation	0.476	0.476

All 12 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: AlphaPeptDeep retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.129 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.1277 to 0.1300. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaPeptDeep (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'MassIVE-KB', row 'AlphaPeptDeep', column 'Med. SA'
Configuration: AlphaPeptDeep retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.129 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaPeptDeep (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'AlphaPeptDeep', column group 'MassIVE-KB', column 'SA'
Configuration: FastSpel retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.476 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.4752 to 0.4762. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FastSpel (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'MassIVE-KB', row 'FastSpel', column 'Med. SA'
Configuration: FastSpel retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.476 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FastSpel (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'FastSpel', column group 'MassIVE-KB', column 'SA'
Configuration: PredFull retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.167 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.1666 to 0.1680. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'MassIVE-KB', row 'PredFull', column 'Med. SA'
Configuration: PredFull retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.167 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'PredFull', column group 'MassIVE-KB', column 'SA'
Configuration: Prosit retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.0995 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.0984 to 0.1006. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Prosit (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'MassIVE-KB', row 'Prosit', column 'Med. SA'
Configuration: Prosit retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.1 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Prosit (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'Prosit', column group 'MassIVE-KB', column 'SA'
Configuration: Prosit Transformer retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.0977 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.0969 to 0.0986. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Prosit Transformer (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'MassIVE-KB', row 'Prosit Trans.', column 'Med. SA'
Configuration: Prosit Transformer retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.098 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Prosit Transformer (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'Prosit Trans.', column group 'MassIVE-KB', column 'SA'
Configuration: UniSpec retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.337 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.3365 to 0.3374. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source UniSpec (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'MassIVE-KB', row 'UniSpec', column 'Med. SA'
Configuration: UniSpec retrained on MassIVE-KB (PepSpecBench)	Protocol: PepSpecBench MassIVE-KB-Mini test split, median SA Dataset: PepSpecBench MassIVE-KB-Mini test split	0.337 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source UniSpec (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'UniSpec', column group 'MassIVE-KB', column 'SA'

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Methods and evaluation design

Procedure, tasks and evaluated configurations

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.

External evaluations: 6

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

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

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

Select an upstream conventional reference after reviewing the full protocol

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 (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-23-5347695500ed. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

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.

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Original source · arXiv:2605.01945v1 (submitted 2026-05-03), arXiv HTML rendering

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-otheromics-20261011-pepspecbench-protocol-massive-kb-sa

areas: proteins-complexes
contexts: research
protocol: Predict fragment intensities for each spectrum, project to the shared canonical b/y space, mask invalid positions, compute SA per spectrum and take the median.
version: PepSpecBench v1
metric: spectral-angle
metric direction: lower
unit: unitless
metric qualifier: median over spectra, shared canonical fragment space
source locator: Section 3.3 (metrics and evaluation protocol); Table 2
limitations: Preprint.; Medians, not means.

Related records

part of: PepSpecBench
uses data: PepSpecBench MassIVE-KB-Mini test split
assessment: AlphaPeptDeep (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA
assessment: FastSpel (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA
assessment: PredFull (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA
assessment: Prosit (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA
assessment: Prosit Transformer (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA
assessment: UniSpec (trained on MassIVE-KB) on MassIVE-KB-Mini test split, SA

Suggest a correction