rewirebio.iobenchmarks
Result

Fingerprint cosine similarity (Morgan radius 2, 4096 bits; raw prediction before thresholding; mean over the full test split) of Nearest neighbour, assumption (3), Modified cosine + sub-formula on MassSpecGym, scaffold split (Khoo 2026)

0.519 Fingerprint cosine similarity (Morgan radius 2, 4096 bits; raw prediction before thresholding; mean over the full test split)

Methods

Tested configuration
Nearest neighbour, assumption (3), Modified cosine + sub-formula
Protocol
Fingerprint prediction from MS/MS, MassSpecGym scaffold split, assumption (3) (Khoo 2026)
Dataset
MassSpecGym, scaffold split (Khoo 2026)
Procedure
Fingerprint prediction from MS/MS, MassSpecGym scaffold split, assumption (3) (Khoo 2026)
Evaluation
Nearest neighbour (Modified cosine + sub-formula), assumption (3), MassSpecGym scaffold
Coverage
Not reported scored / Not reported eligible
Uncertainty
Not reported by the source
Evidence
Author-reported evaluation · source checkedNearest-neighbour baselines for fingerprint prediction from MS/MS spectra under different assumptions · Table 2 assumption (3) row 'Modified cosine + sub-formula', column 'MassSpecGym' / 'Scaffold'

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
Scaffold split test
Adaptation
None (retrieval)
Scoring implementation
Supplementary Note S1 formulas

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 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Reported result
0.519
Individual claims
Nearest-neighbour baselines for fingerprint prediction from MS/MS spectra under different assumptions

Original source ↗

Table 2 assumption (3) row 'Modified cosine + sub-formula', column 'MassSpecGym' / 'Scaffold'

Version: arXiv 2610.02249v1, submitted 2026-09-30
Retrieved: 2026-10-11T00:44:10Z

source checked

["source-hash-verification","pdf-text-parse","independent-cell-check"] · 2026-10-12

author reported

Audit details

Extraction: Extracted from the pinned PDF text layer (pdftotext 26.08.0 -layout) by extract/khoo2026.py with header rows and the 16 row labels asserted. Independent review 2026-10-12: value, locator, metric, unit, direction and linked configuration and protocol checked.

Field: attributes.printed_value

Source artifact SHA-256: 19c0dddb0e789f0dce3cdae73604206a0eab09f7ce411881108db6b937374f1e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Extraction artifact SHA-256: 19c0dddb0e789f0dce3cdae73604206a0eab09f7ce411881108db6b937374f1e

Extraction artifact

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: lit20261011-khoo2026-result-t2-massspecgym-scaffold-a3-modified-cosine-sub-formula

metric
fingerprint-cosine-similarity
metric direction
higher
unit
unitless
printed value
0.519
numeric value
0.519
metric qualifier
Morgan radius 2, 4096 bits; raw prediction before thresholding; mean over the full test split
source locator
Table 2 assumption (3) row 'Modified cosine + sub-formula', column 'MassSpecGym' / 'Scaffold'
missing metadata
uncertainty: reason: unreported
review
method: source-hash-verification; pdf-text-parse; independent-cell-check; method note: Re-downloaded the arXiv PDF and matched its SHA-256 and the archived gzip. An independent regex parse of pdftotext -layout found the 32 data rows and compared all 128 cells (value, metric, assumption, dataset and split links, configuration) 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-other; no human review claimed; date: 2026-10-12; artifact sha256: 19c0dddb0e789f0dce3cdae73604206a0eab09f7ce411881108db6b937374f1e; retrieval url: https://arxiv.org/pdf/2610.02249v1; note: Extraction: Extracted from the pinned PDF text layer (pdftotext 26.08.0 -layout) by extract/khoo2026.py with header rows and the 16 row labels asserted. Independent review 2026-10-12: value, locator, metric, unit, direction and linked configuration and protocol checked.
Related records

Suggest a correction