Top-1 accuracy (retrieval) of DreaMS spectral encoder aligned to frozen ChemBERTa, corrected candidate canonicalization (MassSpecGym in the Wild) on MassSpecGym test fold, formula-known retrieval candidates (bonus) (MassSpecGym in the Wild)
6.70 (6.09-7.35)% Top-1 accuracy (retrieval)
Methods
- Tested configuration
- DreaMS spectral encoder aligned to frozen ChemBERTa, corrected candidate canonicalization (MassSpecGym in the Wild)
- Protocol
- MassSpecGym formula-known retrieval (bonus), Hit rate@1 (MassSpecGym in the Wild Table 3)
- Dataset
- MassSpecGym test fold, formula-known retrieval candidates (bonus) (MassSpecGym in the Wild)
- Procedure
- MassSpecGym formula-known retrieval (bonus), Hit rate@1 (MassSpecGym in the Wild Table 3)
- Evaluation
- DreaMS spectral encoder aligned to frozen ChemBERTa, corrected candidate canonicalization on MassSpecGym formula-retrieval (Hit rate@1)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- 99.9% CI 6.09 to 7.35. Range printed in parentheses after the mean. Appendix 'Confidence Intervals': 99.9% bootstrap interval over 20,000 resamples of the test set.
- Evidence
- Author-reported evaluation · source checkedMassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery · Table 3, section 'Exploiting Canonicalization Artifacts (Not Valid Under Corrected Candidate Canonicalization)', row '(1) DreaMS + ChemBERTa Alignment (corrected)', column 'Hit rate@1'
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
- MassSpecGym test fold
- Adaptation
- Not reported
- 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 6.70 (6.09-7.35)% Individual claims | MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery Table 3, section 'Exploiting Canonicalization Artifacts (Not Valid Under Corrected Candidate Canonicalization)', row '(1) DreaMS + ChemBERTa Alignment (corrected)', column 'Hit rate@1' Version: arXiv:2606.19624v1 (submitted 2026-06-17), arXiv HTML rendering | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-12 author reported Audit detailsExtraction: Parsed the <td> cells of the pinned arXiv HTML table with extract/extract_msgwild.py; row label, column header and grey text style taken from the same table. Table 3 body row 19. Independent review 2026-10-12: value, locator, metric, unit, direction and linked configuration and protocol checked. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
Sources and history
Release 2026-10-23-5347695500ed · Record review: source checked
1 source record and release history
- MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery · Original source · arXiv:2606.19624v1 (submitted 2026-06-17), arXiv HTML rendering
Technical metadata and extraction receipts
Stable ID: lit-otheromics-20261011-msgwild-result-dreams-spectral-encoder-aligned-to-frozen-chemberta-corrected-candidate-canonicalization-formula-retrieval-hit-rate-1
- metric
- top-1-accuracy
- metric direction
- higher
- unit
- percent
- printed value
- 6.70 (6.09-7.35)%
- source locator
- Table 3, section 'Exploiting Canonicalization Artifacts (Not Valid Under Corrected Candidate Canonicalization)', row '(1) DreaMS + ChemBERTa Alignment (corrected)', column 'Hit rate@1'
- 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, 3 and 9 compared all 176 cells (printed and numeric values, CI bounds, grey state, metric, unit and direction) with no mismatch; a seeded sample of 40 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: 47f329399853bdd2a513707b97271dfd8875271be383168effde1b0f13efb0d2; retrieval url: https://arxiv.org/html/2606.19624v1; note: Extraction: Parsed the <td> cells of the pinned arXiv HTML table with extract/extract_msgwild.py; row label, column header and grey text style taken from the same table. Table 3 body row 19. Independent review 2026-10-12: value, locator, metric, unit, direction and linked configuration and protocol checked.
- numeric value
- 6.70
- metric qualifier
- retrieval
- uncertainty
- type: confidence_interval; lower: 6.09; upper: 7.35; printed: 6.70 (6.09-7.35)%; method: bootstrap; note: Range printed in parentheses after the mean. Appendix 'Confidence Intervals': 99.9% bootstrap interval over 20,000 resamples of the test set.; level: 0.999; resamples: 20000