26.87 (26.66-27.11) Top-10 MCES
SELFIES Transformer: Top-10 MCES on MassSpecGym · formula
- Tested configuration
- SELFIES Transformer (formula)
- Protocol
- MassSpecGym · formula (MassSpecGym De novo molecule generation)
- Dataset
- MassSpecGym · formula
- Procedure
- Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split
- Evaluation
- SELFIES Transformer (formula): MassSpecGym · formula
- Coverage
- scored: unreported; eligible: unreported
- Uncertainty
- type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 26.66; upper: 27.11
- Evidence
- Author-reported evaluation · source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-10 MCES
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: needs review. Source checked does not mean independently reproduced.
Reproduction
- Split
- MCES single-linkage molecular clustering at threshold 10; fixed held-out test split
- Adaptation
- MassSpecGym paper baseline; spectrum-conditioned Transformer; molecular formula provided
- Scoring implementation
- Not reported
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 26.87 (26.66-27.11) Individual claims | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2, bonus formula challenge, SELFIES Transformer, Top-10 MCES Version: 2410.23326v1 | source checked Primary-table transcription and separate automated source review · 2026-09-17 author reported Audit detailsSource checked does not mean experimentally reproduced. Field: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: source checked
1 source records and release history
- MassSpecGym: A benchmark for the discovery and identification of molecules · Original source · 2410.23326v1
Technical metadata and extraction receipts
Stable ID: paper-result-0cba6df8abf3e80c3e
- areas
- metabolomics
- printed value
- 26.87 (26.66-27.11)
- numeric value
- 26.87
- metric
- Top-10 MCES
- metric direction
- lower
- unit
- edge-edit distance
- uncertainty
- type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 26.66; upper: 27.11
- eligible count
- Not reported
- scored count
- Not reported
- reported population
- Not reported
- source locator
- Table 2, bonus formula challenge, SELFIES Transformer, Top-10 MCES
- source occurrences
- source id: part2-massspecgym-arxiv-v1; locator: Table 2, bonus formula challenge, SELFIES Transformer, Top-10 MCES
- review
- method: Primary-table transcription and separate automated source review; date: 2026-09-17; note: Source checked does not mean experimentally reproduced.
- missing metadata
- scored count: unreported; eligible count: unextracted; checkpoint revision: unextracted; uncertainty: inapplicable