Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage.
These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.
Release 2026-09-29-06401fd5b220 · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
3 evaluations · 18 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 18.25 (18.14-18.35) Top-10 MCES edge-edit distance · lower Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 18.14; upper: 18.35 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, Random chemical generation, Top-10 MCES |
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.03 (0.03 - 0.04) Top-1 Tanimoto dimensionless · higher Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.03; upper: 0.04 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SMILES Transformer, Top-1 Tanimoto |
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 26.87 (26.66-27.11) Top-10 MCES edge-edit distance · lower Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 26.66; upper: 27.11 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-10 MCES |
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.10 (0.09 - 0.10) Top-10 Tanimoto dimensionless · higher Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.09; upper: 0.10 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SMILES Transformer, Top-10 Tanimoto |
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0 Top-10 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, Random chemical generation, Top-10 accuracy |
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0 Top-10 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-10 accuracy |
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 21.11 (20.97-21.26) Top-1 MCES edge-edit distance · lower Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 20.97; upper: 21.26 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, Random chemical generation, Top-1 MCES |
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.11 (0.11 - 0.11) Top-10 Tanimoto dimensionless · higher Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.11; upper: 0.11 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, Random chemical generation, Top-10 Tanimoto |
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0 Top-1 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, Random chemical generation, Top-1 accuracy |
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0 Top-10 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SMILES Transformer, Top-10 accuracy |
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.08 (0.08 - 0.08) Top-1 Tanimoto dimensionless · higher Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.08; upper: 0.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-1 Tanimoto |
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.08 (0.08 - 0.08) Top-1 Tanimoto dimensionless · higher Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.08; upper: 0.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, Random chemical generation, Top-1 Tanimoto |
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 79.39 (78.64-80.08) Top-1 MCES edge-edit distance · lower Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 78.64; upper: 80.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SMILES Transformer, Top-1 MCES |
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 52.13 (51.45-52.81) Top-10 MCES edge-edit distance · lower Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 51.45; upper: 52.81 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SMILES Transformer, Top-10 MCES |
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0 Top-1 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SMILES Transformer, Top-1 accuracy |
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.13 (0.13 - 0.13) Top-10 Tanimoto dimensionless · higher Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.13; upper: 0.13 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-10 Tanimoto |
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0 Top-1 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-1 accuracy |
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 38.88 (38.57-39.20) Top-1 MCES edge-edit distance · lower Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 38.57; upper: 39.20 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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 Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, bonus formula challenge, SELFIES Transformer, Top-1 MCES |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.reported_population Not reported Context-only references | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2: Top-1 accuracy, formula Version: 2410.23326v1 | missing or unspecified No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.source_locator Table 2: Top-1 accuracy, formula Context-only references | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2: Top-1 accuracy, formula Version: 2410.23326v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.split MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Context-only references | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2: Top-1 accuracy, formula Version: 2410.23326v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.subset formula Context-only references | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2: Top-1 accuracy, formula Version: 2410.23326v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| description Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage. Context-only references | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2: Top-1 accuracy, formula Version: 2410.23326v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| name MassSpecGym · formula Context-only references | MassSpecGym: A benchmark for the discovery and identification of molecules Table 2: Top-1 accuracy, formula Version: 2410.23326v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
Stable ID: paper-dataset-3f9a5b3d0316153887