rewire.it
Protocol

FLIP2 hydro low-to-high; held-out test set · hydro

Source-specific evaluation. No equivalence to other releases, protocols or model families is inferred.

9 evaluations · 18 metric rows

Published comparisons

Each figure keeps its source, protocol, dataset and metric together. Results from different protocols are shown separately, without a pooled ranking.

FLIP2 hydro low-to-high; held-out test set · hydro: spearman

spearman (correlation) · Higher values are better for this metric.

Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.

Evaluation protocol · hydro

  1. Ridge (one-hot) · Configuration · Author-reported evaluation0.146
  2. Dayhoff likelihood · Configuration · Author-reported evaluation0.308
  3. ESM2-650M likelihood · Configuration · Author-reported evaluation−0.038
  4. CARP-640M likelihood · Configuration · Author-reported evaluation0.284

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot); column spearman through Table A11; row ESMC-300M naive supervised; column spearman
Values, uncertainty and evidence
spearman: original source values
Tested entityPrinted valueUncertaintyEvidence
Ridge (one-hot) · Configuration0.146 correlationNot reportedAuthor-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot); column spearman
Ridge (one-hot + likelihoods) · Configuration0.205 correlationNot reportedAuthor-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot + likelihoods); column spearman
Dayhoff likelihood · Configuration0.308 correlationNot reportedAuthor-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Dayhoff likelihood; column spearman
ESM2-650M likelihood · Configuration−0.038 correlationNot reportedAuthor-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESM2-650M likelihood; column spearman
CARP-640M likelihood · Configuration0.284 correlationNot reportedAuthor-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M likelihood; column spearman
CARP-640M supervised · Configuration0.188 ± 0.071 correlationprinted spread: 0.071; type: unreported; value: 0.071Author-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M supervised; column spearman
CARP-640M naive supervised · Configuration0.188 ± 0.202 correlationprinted spread: 0.202; type: unreported; value: 0.202Author-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M naive supervised; column spearman
ESMC-300M supervised · Configuration0.099 ± 0.194 correlationprinted spread: 0.194; type: unreported; value: 0.194Author-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESMC-300M supervised; column spearman
ESMC-300M naive supervised · Configuration0.270 ± 0.048 correlationprinted spread: 0.048; type: unreported; value: 0.048Author-reported evaluation · source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESMC-300M naive supervised; column spearman
Scope and limitations
  • Source-specific evaluation. No equivalence to other releases, protocols or model families is inferred.
  • Exact source-defined evaluation scope; reported scores are not rewire reproductions.
  • Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.

Source transcription and grouping reviewed by automated source review on 2026-09-19. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-19-eb6149e5d766 · 9 evaluations · 18 metric rows. Different protocols are not a single leaderboard. Charts retain each source table’s protocol and dataset.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
ESM2-650M likelihood · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.865 ndcg

Unit: unitless · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESM2-650M likelihood; column ndcg

Source checking is not independent reproduction.

−0.038 spearman

Unit: correlation · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESM2-650M likelihood; column spearman

Source checking is not independent reproduction.

CARP-640M likelihood · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.284 spearman

Unit: correlation · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M likelihood; column spearman

Source checking is not independent reproduction.

0.921 ndcg

Unit: unitless · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M likelihood; column ndcg

Source checking is not independent reproduction.

CARP-640M supervised · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.188 ± 0.071 spearman

Unit: correlation · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.071; type: unreported; value: 0.071

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M supervised; column spearman

Source checking is not independent reproduction.

0.887 ± 0.007 ndcg

Unit: unitless · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.007; type: unreported; value: 0.007

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M supervised; column ndcg

Source checking is not independent reproduction.

ESMC-300M naive supervised · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.905 ± 0.008 ndcg

Unit: unitless · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.008; type: unreported; value: 0.008

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESMC-300M naive supervised; column ndcg

Source checking is not independent reproduction.

0.270 ± 0.048 spearman

Unit: correlation · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.048; type: unreported; value: 0.048

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESMC-300M naive supervised; column spearman

Source checking is not independent reproduction.

Ridge (one-hot) · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.887 ndcg

Unit: unitless · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot); column ndcg

Source checking is not independent reproduction.

0.146 spearman

Unit: correlation · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot); column spearman

Source checking is not independent reproduction.

CARP-640M naive supervised · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.188 ± 0.202 spearman

Unit: correlation · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.202; type: unreported; value: 0.202

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M naive supervised; column spearman

Source checking is not independent reproduction.

0.896 ± 0.032 ndcg

Unit: unitless · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.032; type: unreported; value: 0.032

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M naive supervised; column ndcg

Source checking is not independent reproduction.

Ridge (one-hot + likelihoods) · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.903 ndcg

Unit: unitless · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot + likelihoods); column ndcg

Source checking is not independent reproduction.

0.205 spearman

Unit: correlation · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Ridge (one-hot + likelihoods); column spearman

Source checking is not independent reproduction.

ESMC-300M supervised · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.099 ± 0.194 spearman

Unit: correlation · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.194; type: unreported; value: 0.194

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESMC-300M supervised; column spearman

Source checking is not independent reproduction.

0.870 ± 0.030 ndcg

Unit: unitless · Direction: higher

Aggregation: mean of five random-seed fits (Section 4.3)

Uncertainty: printed spread: 0.030; type: unreported; value: 0.03

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESMC-300M supervised; column ndcg

Source checking is not independent reproduction.

Dayhoff likelihood · FLIP2 hydro low-to-high; held-out test set · hydro

FLIP2 hydro low-to-high; held-out test set

Author-reported evaluation · Evaluation metadata: discovered

0.308 spearman

Unit: correlation · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Dayhoff likelihood; column spearman

Source checking is not independent reproduction.

0.924 ndcg

Unit: unitless · Direction: higher

Aggregation: reported point estimate

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row Dayhoff likelihood; column ndcg

Source checking is not independent reproduction.

Overview

Source-specific evaluation. No equivalence to other releases, protocols or model families is inferred.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

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 2026-09-19-eb6149e5d766
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-flip2

Individual claims
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications

Original source ↗

Table A11; row Ridge (one-hot); column spearman

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.183348+00:00

source checked

ai assisted source review · 2026-09-19

Audit details

Field: links:part_of:discovery-benchmark-flip2

Claim: acquired-membership-7885cc0932f28eff8c6d

Source artifact SHA-256: d0e61ca27863c023adddcc225a3e4af1718f2e3fdfe3642bef89c24c93621a17

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-19-eb6149e5d766 · Record review: discovered

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: acquired-protocol-2a25c278d301f1b27a06

source locator
Table A11; row Ridge (one-hot); column spearman
procedure
FLIP2 hydro low-to-high; held-out test set
comparison panels
id: acquired-figure-200f7eb21051a74ea52a; title: FLIP2 hydro low-to-high; held-out test set · hydro: spearman; protocol id: acquired-protocol-2a25c278d301f1b27a06; dataset id: acquired-dataset-ecef09ad02eca7267357; metric: spearman; unit: correlation; direction: higher; result ids: acquired-result-b7c07963ef3556551ee1; acquired-result-c7e4947703ed04830bf5; acquired-result-c2e2b82e5f4d8f8c2f78; acquired-result-b4dbfaa563abc2f4fe61; acquired-result-0b38908cff39ab1b76dc; acquired-result-453c7dedd32708493065; acquired-result-8a936c39f21f31fda620; acquired-result-9421ecde5bf3905bc7f6; acquired-result-befec5a6593c46f0dfbf; source ids: evidence-expansion-flip2-d0e61ca2; source locator: Table A11; row Ridge (one-hot); column spearman through Table A11; row ESMC-300M naive supervised; column spearman; context: Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.; caveats: Source-specific evaluation. No equivalence to other releases, protocols or model families is inferred.; Exact source-defined evaluation scope; reported scores are not rewire reproductions.; Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.; review: method: automated_source_review; date: 2026-09-19; id: acquired-figure-b8e8f3f48dc6095e1974; title: FLIP2 hydro low-to-high; held-out test set · hydro: ndcg; protocol id: acquired-protocol-2a25c278d301f1b27a06; dataset id: acquired-dataset-ecef09ad02eca7267357; metric: ndcg; unit: unitless; direction: higher; result ids: acquired-result-85c1be37143dc131b759; acquired-result-8b24cea4501fbbd02b86; acquired-result-f706c5f8292f73a3001c; acquired-result-03788bc9d1fbf6b35d16; acquired-result-255dd5eab162987dcf18; acquired-result-71e822a5074ecb4a7a8d; acquired-result-deea4e5bcce6f48187eb; acquired-result-aebb0bf2c71fa0266a46; acquired-result-6f6ae21a3350077ddb64; source ids: evidence-expansion-flip2-d0e61ca2; source locator: Table A11; row Ridge (one-hot); column ndcg through Table A11; row ESMC-300M naive supervised; column ndcg; context: Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.; caveats: Source-specific evaluation. No equivalence to other releases, protocols or model families is inferred.; Exact source-defined evaluation scope; reported scores are not rewire reproductions.; Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.; review: method: automated_source_review; date: 2026-09-19
scope limitations
Exact source-defined evaluation scope; reported scores are not rewire reproductions.
Related records

Suggest a correction