rewire.it
Dataset

MassSpecGym · main

Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

Evaluation results

Release 2026-09-17-d277315f7d76 · 4 evaluations · 20 metric rows. Different protocols are not a single leaderboard.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
GNN (main): MassSpecGym · main

Predict a spectrum from a molecule under measurement conditions. Metadata-complete simulation subset; simulation-derived retrieval is distinct from direct molecule retrieval in Table 3. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split

Author-reported evaluation · Evaluation metadata: needs review

0.19 (0.18-0.20) Cosine similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.18; upper: 0.20

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, GNN, Cosine similarity

Source checking is not independent reproduction.

3.95 (3.37-4.62)% Hit rate @1

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 3.37; upper: 4.62

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, GNN, Hit rate @1

Source checking is not independent reproduction.

26.27 (24.83-27.82)% Hit rate @20

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 24.83; upper: 27.82

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, GNN, Hit rate @20

Source checking is not independent reproduction.

11.92 (10.87-13.00)% Hit rate @5

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 10.87; upper: 13.00

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, GNN, Hit rate @5

Source checking is not independent reproduction.

0.44 (0.44-0.45) Jensen-Shannon similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.44; upper: 0.45

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, GNN, Jensen-Shannon similarity

Source checking is not independent reproduction.

FraGNNet (main): MassSpecGym · main

Predict a spectrum from a molecule under measurement conditions. Metadata-complete simulation subset; simulation-derived retrieval is distinct from direct molecule retrieval in Table 3. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split

Author-reported evaluation · Evaluation metadata: needs review

0.63 (0.63-0.64) Jensen-Shannon similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.63; upper: 0.64

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FraGNNet, Jensen-Shannon similarity

Source checking is not independent reproduction.

0.52 (0.51-0.53) Cosine similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.51; upper: 0.53

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FraGNNet, Cosine similarity

Source checking is not independent reproduction.

83.58 (82.34-84.75)% Hit rate @20

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 82.34; upper: 84.75

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FraGNNet, Hit rate @20

Source checking is not independent reproduction.

72.56 (71.18-74.00)% Hit rate @5

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 71.18; upper: 74.00

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FraGNNet, Hit rate @5

Source checking is not independent reproduction.

46.64 (44.98-48.26)% Hit rate @1

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 44.98; upper: 48.26

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FraGNNet, Hit rate @1

Source checking is not independent reproduction.

Precursor m/z (main): MassSpecGym · main

Predict a spectrum from a molecule under measurement conditions. Metadata-complete simulation subset; simulation-derived retrieval is distinct from direct molecule retrieval in Table 3. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split

Author-reported evaluation · Evaluation metadata: needs review

0.38 (0.21-0.62)% Hit rate @1

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.21; upper: 0.62

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, Precursor m/z, Hit rate @1

Source checking is not independent reproduction.

1.72 (1.32-2.18)% Hit rate @5

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 1.32; upper: 2.18

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, Precursor m/z, Hit rate @5

Source checking is not independent reproduction.

7.17 (6.32-8.04)% Hit rate @20

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 6.32; upper: 8.04

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, Precursor m/z, Hit rate @20

Source checking is not independent reproduction.

0.15 (0.14-0.17) Cosine similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.14; upper: 0.17

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, Precursor m/z, Cosine similarity

Source checking is not independent reproduction.

0.41 (0.40-0.42) Jensen-Shannon similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.40; upper: 0.42

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, Precursor m/z, Jensen-Shannon similarity

Source checking is not independent reproduction.

FFN Fingerprint (main): MassSpecGym · main

Predict a spectrum from a molecule under measurement conditions. Metadata-complete simulation subset; simulation-derived retrieval is distinct from direct molecule retrieval in Table 3. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split

Author-reported evaluation · Evaluation metadata: needs review

8.44 (7.56-9.34)% Hit rate @1

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 7.56; upper: 9.34

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FFN Fingerprint, Hit rate @1

Source checking is not independent reproduction.

0.48 (0.47-0.48) Jensen-Shannon similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.47; upper: 0.48

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FFN Fingerprint, Jensen-Shannon similarity

Source checking is not independent reproduction.

38.57 (36.99-40.23)% Hit rate @20

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 36.99; upper: 40.23

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FFN Fingerprint, Hit rate @20

Source checking is not independent reproduction.

21.43 (20.10-22.79)% Hit rate @5

Unit: percent · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 20.10; upper: 22.79

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FFN Fingerprint, Hit rate @5

Source checking is not independent reproduction.

0.25 (0.24-0.26) Cosine similarity

Unit: dimensionless · Direction: higher

Uncertainty: type: bootstrap confidence interval; level: 0.999; resamples: 20000; lower: 0.24; upper: 0.26

Scored: Not reported · Eligible: Not reported

source checkedMassSpecGym: A benchmark for the discovery and identification of molecules · Table 4, main challenge, FFN Fingerprint, Cosine similarity

Source checking is not independent reproduction.

Evidence table

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

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statementOriginal source and locationReview and provenance
attributes.reported_population

No value recorded

Context-only references
MassSpecGym: A benchmark for the discovery and identification of molecules

Original source ↗

Table 4: Cosine similarity, main

Version: 2410.23326v1
Retrieved: 2026-09-17T07:56:11.146650+00:00

missing or unspecified

No individual claim review recorded

Audit details

Field: attributes.reported_population

Source artifact SHA-256: 82176d50e8947c8b9baa2a0d91493f5680c0e4c7e25a2266ff7879f48a58c40c

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

attributes.source_locator

Table 4: Cosine similarity, main

Context-only references
MassSpecGym: A benchmark for the discovery and identification of molecules

Original source ↗

Table 4: Cosine similarity, main

Version: 2410.23326v1
Retrieved: 2026-09-17T07:56:11.146650+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 82176d50e8947c8b9baa2a0d91493f5680c0e4c7e25a2266ff7879f48a58c40c

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

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

Original source ↗

Table 4: Cosine similarity, main

Version: 2410.23326v1
Retrieved: 2026-09-17T07:56:11.146650+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.split

Source artifact SHA-256: 82176d50e8947c8b9baa2a0d91493f5680c0e4c7e25a2266ff7879f48a58c40c

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

attributes.subset

main

Context-only references
MassSpecGym: A benchmark for the discovery and identification of molecules

Original source ↗

Table 4: Cosine similarity, main

Version: 2410.23326v1
Retrieved: 2026-09-17T07:56:11.146650+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.subset

Source artifact SHA-256: 82176d50e8947c8b9baa2a0d91493f5680c0e4c7e25a2266ff7879f48a58c40c

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

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

Original source ↗

Table 4: Cosine similarity, main

Version: 2410.23326v1
Retrieved: 2026-09-17T07:56:11.146650+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 82176d50e8947c8b9baa2a0d91493f5680c0e4c7e25a2266ff7879f48a58c40c

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

name

MassSpecGym · main

Context-only references
MassSpecGym: A benchmark for the discovery and identification of molecules

Original source ↗

Table 4: Cosine similarity, main

Version: 2410.23326v1
Retrieved: 2026-09-17T07:56:11.146650+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 82176d50e8947c8b9baa2a0d91493f5680c0e4c7e25a2266ff7879f48a58c40c

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

Download this release
Technical metadata and extraction receipts

Stable ID: paper-dataset-537c7d5a2018d12af3

areas
metabolomics
split
MCES single-linkage molecular clustering at threshold 10; fixed held-out test split
subset
main
reported population
Not reported
source locator
Table 4: Cosine similarity, main
missing metadata
manifest: unextracted; scored count: unreported
entity classification
review date: 2026-09-17; rationale: This record identifies a biological data collection or source-labelled evaluation cohort. Keep its dataset identity; split, assay, taxonomic level, candidate restrictions and comparison context remain attributes rather than automatically becoming new entity kinds.; source ids: part2-massspecgym-arxiv-v1; source locator: Table 4: Cosine similarity, main; ambiguities: The formula/main label describes task input or candidate constraints in some MassSpecGym tables, not necessarily a different biological population. Preserve the paper-specific data identity and do not infer subset equivalence.
Related records

Suggest a correction