Result

Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) of Prosit retrained on PROSPECT (PepSpecBench) on PepSpecBench PROSPECT-Mini test split

0.138 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14))

Methods

Tested configuration: Prosit retrained on PROSPECT (PepSpecBench)
Protocol: PepSpecBench PROSPECT-Mini test split, median SA
Dataset: PepSpecBench PROSPECT-Mini test split
Procedure: PepSpecBench PROSPECT-Mini test split, median SA
Evaluation: Prosit (trained on PROSPECT) on PROSPECT-Mini test split, SA
Coverage: Not reported scored / Not reported eligible
Uncertainty: 95% CI 0.1354 to 0.1397. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra.
Evidence: Independent external evaluation · source checkedPepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'PROSPECT', row 'Prosit', column 'Med. SA'

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: Backbone-disjoint test
Adaptation: Retrained on PROSPECT; no adaptation to the evaluation set
Scoring implementation: SA in the shared canonical fragment space

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

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance
Reported result 0.1376 Individual claims	PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction Original source ↗ Table 14, source 'PROSPECT', row 'Prosit', column 'Med. SA' Version: arXiv:2605.01945v1 (submitted 2026-05-03), arXiv HTML rendering Retrieved: 2026-10-11T21:27:08Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-12 independent paper Audit details Extraction: Parsed the <td> cells of the pinned arXiv HTML table with extract/extract_pepspecbench.py; row label and column header taken from the same table. Table 14 body row 7. Independent review 2026-10-12: value, locator, metric, unit, direction and linked configuration and protocol checked. Field: `attributes.printed_value` Source artifact SHA-256: `af7ed6d4470f0d4f60fccbe55103e72b19c258e53f9dd26c0c0e152a2ef18d81` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `af7ed6d4470f0d4f60fccbe55103e72b19c258e53f9dd26c0c0e152a2ef18d81` Extraction artifact

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-result-prosit-trained-prospect-prospect-sa-t14

metric: spectral-angle
metric direction: lower
unit: unitless
printed value: 0.1376
source locator: Table 14, source 'PROSPECT', row 'Prosit', column 'Med. SA'
review: method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the arXiv HTML and PDF and matched their SHA-256. An independent html.parser read of Tables 2, 4 and 14 compared all 168 cells (value, metric, direction, training source, configuration, OOD protocol and Table 14 CI bounds) with no mismatch; a seeded sample of 42 cells was read against the rendered PDF pages and all matched.; reviewer: claude; reviewer note: Claude review agent reviewer-ro-2, independent of the extractor lit-rna-otheromics; no human review claimed; date: 2026-10-12; artifact sha256: af7ed6d4470f0d4f60fccbe55103e72b19c258e53f9dd26c0c0e152a2ef18d81; retrieval url: https://arxiv.org/html/2605.01945v1; note: Extraction: Parsed the <td> cells of the pinned arXiv HTML table with extract/extract_pepspecbench.py; row label and column header taken from the same table. Table 14 body row 7. Independent review 2026-10-12: value, locator, metric, unit, direction and linked configuration and protocol checked.
numeric value: 0.1376
metric qualifier: median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)
uncertainty: type: confidence_interval; lower: 0.1354; upper: 0.1397; level: 0.95; method: bootstrap; resamples: 1000; printed: 0.1354 to 0.1397; source column: 95% CI (lo), 95% CI (hi); note: Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra.

Related records

evaluation: Prosit (trained on PROSPECT) on PROSPECT-Mini test split, SA

Suggest a correction