Spearman (retrospective, in-sample statistic at the Matthews-correlation-maximising perplexity threshold, high expression defined as at least 0.08 mg) of ESM2-150M perplexity as a VHH expression classifier on Retrospective VHH expression measurements
−0.602 Spearman (retrospective, in-sample statistic at the Matthews-correlation-maximising perplexity threshold, high expression defined as at least 0.08 mg)
Methods
- Tested configuration
- ESM2-150M perplexity as a VHH expression classifier
- Protocol
- VHH expression against ESM2-150M perplexity: Spearman correlation
- Dataset
- Retrospective VHH expression measurements
- Evaluation
- ESM2-150M perplexity against measured VHH expression: Spearman rank correlation
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source: No interval or p-value is printed for these statistics.
- Evidence
- Author-reported evaluation · source checkedTorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Supplementary Figure S4 caption, panel b (page 32), fragment "Spearman ρ = −0.602"
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
- Not reported
- Adaptation
- Perplexity swept as a one-dimensional classifier, with the operating threshold chosen to maximise the Matthews correlation coefficient
- Scoring implementation
- ESM2-150M perplexity; high expression defined as a total of at least 0.08 mg
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 −0.602 Individual claims | TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) Supplementary Figure S4 caption, panel b (page 32), fragment "Spearman ρ = −0.602" Version: arXiv:2609.19770v1, submitted 17 September 2026 | source checked ["independent-cell-check","transcription","pdf-text-parse","source-hash-verification"] · 2026-11-16T01:05:00Z author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here. Extraction artifact SHA-256: |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Original source · arXiv:2609.19770v1, submitted 17 September 2026
Technical metadata and extraction receipts
Stable ID: torchcraft-20261115-result-vhh-expression-spearman
- areas
- proteins-complexes
- contexts
- research
- claim scope
- A retrospective in-sample statistic on unreleased expression measurements, used to set the expression proxy in the VHH benchmark criterion.
- metric
- spearman-correlation
- metric direction
- unknown
- metric qualifier
- retrospective, in-sample statistic at the Matthews-correlation-maximising perplexity threshold, high expression defined as at least 0.08 mg
- missing metadata
- denominator: note: The number of sequences behind the statistic is not stated.; reason: unreported; uncertainty: note: No interval or p-value is printed for these statistics.; reason: unreported
- numeric value
- -0.602
- printed value
- −0.602
- review
- artifact sha256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21; method: independent-cell-check; transcription; pdf-text-parse; source-hash-verification; method note: Read by hand from the Supplementary Figure S4 caption in the refetched text layer, then re-checked with data/omics/torchcraft-20261115/review/recheck_values.py, which asserts the fragments 'MCC = 0.598', 'Pearson r = −0.538' and 'Spearman ρ = −0.602' verbatim in the normalised text and matches each to its own result. A negative control that gave the MCC result the Pearson value was rejected. The caption prints the threshold as 6.309 and Appendix A.4.3.2 prints it as 6.31; both are recorded. npm run batch -- check-values lists these values as locator_not_parsed by design, because they are printed in a figure caption. All seven pinned artifacts were re-retrieved by the reviewer on 2026-11-16T00:08Z. Six came back byte-identical to the hash on their source record. The Hugging Face page did not, and cannot: three consecutive fetches gave three different hashes. Normalising its per-request hf-sanitized CSS class hashes leaves one further per-request difference, window.requestId, and the page also prints a download counter; with those normalised the markup is identical. Its licence tag, gate text and dataset card matched the recorded quotations word for word, so the page is a per-retrieval stamp, not a changed page. The pdftotext -layout text layer of the refetched PDF hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b, the value the extractor recorded.; retrieval url: https://arxiv.org/pdf/2609.19770v1; reviewed at: 2026-11-16T01:05:00Z; reviewer: claude; reviewer note: Claude (Opus 5) review agent, independent of the extractor; no human review claimed. Every pinned artifact was re-retrieved and hashed, and every stored value re-read against it. Nothing was reproduced: no design run, score, docking calculation or binding measurement was repeated, and no value was recomputed from source data.
- source locator
- Supplementary Figure S4 caption, panel b (page 32), fragment "Spearman ρ = −0.602"
- unit
- unitless