ProteinBench against ProteinGym on ESM3 and ProteinMPNN: different tasks
Discrepancy review of ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT · pLDDT
explained
Review of discrepancy-f82ed80f71c6f0bd: explained.
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.
31 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Action investigated Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Date 2026-10-23 Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Discrepancy id discrepancy-f82ed80f71c6f0bd Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Claimed field discrepancy_review Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Investigation url https://github.com/rewire-bio/rewire-benchmark-data/issues/205 Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Rationale ProteinBench ranks ProteinMPNN above ESM3 on de novo backbone sequence design (pLDDT and scTM after refolding); the consensus is ProteinGym zero-shot variant effect prediction, where ESM3 leads. Different endpoints; both kept as reported. The same pair also fires the other way round as discrepancy-fed245c475fd08dc, with ProteinGym as the outlier (issue 205). Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Revision 1 Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Source location The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Claimed value explained Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Description Review of discrepancy-f82ed80f71c6f0bd: explained. Context-only references | proteinbench primary benchmark evidence The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6) Version: 2409.06744v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- proteinbench primary benchmark evidence · Original source · 2409.06744v1
Technical metadata and extraction receipts
Stable ID: discrepancy-review-20261023-proteinbench-esm3-proteinmpnn
- areas
- proteins-complexes
- contexts
- research
- field
- discrepancy_review
- discrepancy id
- discrepancy-f82ed80f71c6f0bd
- revision
- 1
- value
- explained
- action
- investigated
- date
- 2026-10-23
- rationale
- ProteinBench ranks ProteinMPNN above ESM3 on de novo backbone sequence design (pLDDT and scTM after refolding); the consensus is ProteinGym zero-shot variant effect prediction, where ESM3 leads. Different endpoints; both kept as reported. The same pair also fires the other way round as discrepancy-fed245c475fd08dc, with ProteinGym as the outlier (issue 205).
- investigation url
- https://github.com/rewire-bio/rewire-benchmark-data/issues/205
- source locator
- The outlier and consensus results of discrepancy-f82ed80f71c6f0bd as published at https://benchmarks.rewirebio.io/contested/discrepancy-f82ed80f71c6f0bd/ (release 2026-10-23-968c8720eea6)
- review
- method: automated-source-review; ai-assisted-source-review; reviewer: claude; reviewer note: Recorded by a Claude agent; no human review claimed.; date: 2026-10-23; method note: Read every outlier and consensus result of the finding, with its protocol, metric, configuration and source, from the published contested-result page, and compared the tasks, settings and configurations on each side. The original papers were not re-opened.; note: Records where the discrepancy stands, not a correction to any result. No result value or status was changed.
Related records
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT · pLDDT
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM · scTM
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-PLDDT · pLDDT
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-SCTM · scTM
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-PLDDT · pLDDT
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-SCTM · scTM
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-PLDDT · pLDDT
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-SCTM · scTM
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-PLDDT · pLDDT
- subject: ESM3 · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-SCTM · scTM
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT · pLDDT
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM · scTM
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-PLDDT · pLDDT
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-SCTM · scTM
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-PLDDT · pLDDT
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-SCTM · scTM
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-PLDDT · pLDDT
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-SCTM · scTM
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-PLDDT · pLDDT
- subject: ProteinMPNN · ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-SCTM · scTM