rewirebio.iobenchmarks
Protocol

Native sequence recovery of designed sequences (HyInv report)

Measure the fraction of scored positions at which a designed sequence carries the native residue.

55 evaluations · 55 results

Overview

An explanatory profile has not yet been reviewed for this record.

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

55 recorded evaluations, 55 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

55 evaluations · 55 results. Different protocols are not a single leaderboard.

Protocol: Native sequence recovery of designed sequences (HyInv report)

Sorted by Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationProtocol and datasetSequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
LM-Design 650M (HyInv report)EvaluationTS500 (500 chains)0.634 (best in column)
LM-Design 650M (HyInv report)EvaluationTS50 (50 chains)0.601
PiFold (HyInv report)EvaluationTS500 (500 chains)0.593
LM-Design 650M (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.587
PiFold (HyInv report)EvaluationTS50 (50 chains)0.564
DPLM-2 3B (HyInv report)EvaluationTS500 (500 chains)0.563
CMLM (HyInv report)EvaluationTS500 (500 chains)0.558
PiFold (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.552
ProteinMPNN (low-noise, grouped) (HyInv report)EvaluationTS500 (500 chains)0.544
DPLM-2 3B (HyInv report)EvaluationTS50 (50 chains)0.536
LM-Design 650M (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.525
CMLM (HyInv report)EvaluationTS50 (50 chains)0.521
LM-Design 650M (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.516
LigandMPNN (HyInv report)EvaluationTS500 (500 chains)0.511
PiFold (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.511
CMLM (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.507
ProteinMPNN (low-noise, grouped) (HyInv report)EvaluationTS50 (50 chains)0.504
PiFold (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.492
ProteinMPNN (low-noise, grouped) (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.485
DPLM-2 3B (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.479
CMLM (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.477
LigandMPNN (HyInv report)EvaluationTS50 (50 chains)0.475
DPLM-2 3B (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.473
ProteinMPNN grouped (HyInv report)EvaluationTS500 (500 chains)0.467
ProteinMPNN (HyInv report)EvaluationTS500 (500 chains)0.466
ProteinZero V2 (ESM1) (HyInv report)EvaluationTS500 (500 chains)0.46
ProteinZero V2 (ESM2) (HyInv report)EvaluationTS500 (500 chains)0.46
HyInv default (HyInv report)EvaluationTS500 (500 chains)0.458
CMLM (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.454
LigandMPNN (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.453
DPLM-2 3B (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.452
ProteinMPNN (low-noise, grouped) (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.449
ProteinMPNN (HyInv report)EvaluationTS50 (50 chains)0.445
ProteinMPNN grouped (HyInv report)EvaluationTS50 (50 chains)0.443
HyInv default (HyInv report)EvaluationTS50 (50 chains)0.44
ProteinZero V2 (ESM1) (HyInv report)EvaluationTS50 (50 chains)0.437
ProteinMPNN (low-noise, grouped) (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.435
ProteinZero V2 (ESM2) (HyInv report)EvaluationTS50 (50 chains)0.435
ProteinMPNN grouped (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.428
ProteinMPNN (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.428
LigandMPNN (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.427
HyInv default (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.421
ProteinZero V2 (ESM1) (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.416
ProteinZero V2 (ESM2) (HyInv report)EvaluationRecentPDB (121 chains from 111 recent PDB entries)0.415
LigandMPNN (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.411
ProteinMPNN (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.398
ProteinMPNN grouped (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.398
ProteinZero V2 (ESM1) (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.391
ProteinZero V2 (ESM2) (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.39
ProteinMPNN grouped (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.388
ProteinMPNN (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.387
HyInv default (HyInv report)EvaluationCATH4.2 test (1,120 chains)0.382
ProteinZero V2 (ESM1) (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.379
ProteinZero V2 (ESM2) (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.379
HyInv default (HyInv report)EvaluationCATH4.3 test (1,882 chains)0.373
All 55 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: CMLM (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
0.454 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CMLM on CATH4.2 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'CMLM', column 'CATH4.2 test' (page 17 of 21)
Configuration: CMLM (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
0.507 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CMLM on CATH4.3 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'CMLM', column 'CATH4.3 test' (page 17 of 21)
Configuration: CMLM (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.477 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CMLM on RecentPDB (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'CMLM', column 'RecentPDB' (page 17 of 21)
Configuration: CMLM (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS50 (50 chains)
0.521 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CMLM on TS50 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'CMLM', column 'TS50' (page 17 of 21)
Configuration: CMLM (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS500 (500 chains)
0.558 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CMLM on TS500 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'CMLM', column 'TS500' (page 17 of 21)
Configuration: DPLM-2 3B (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
0.479 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DPLM-2 3B on CATH4.2 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'DPLM-2 3B', column 'CATH4.2 test' (page 17 of 21)
Configuration: DPLM-2 3B (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
0.473 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DPLM-2 3B on CATH4.3 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'DPLM-2 3B', column 'CATH4.3 test' (page 17 of 21)
Configuration: DPLM-2 3B (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.452 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DPLM-2 3B on RecentPDB (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'DPLM-2 3B', column 'RecentPDB' (page 17 of 21)
Configuration: DPLM-2 3B (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS50 (50 chains)
0.536 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DPLM-2 3B on TS50 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'DPLM-2 3B', column 'TS50' (page 17 of 21)
Configuration: DPLM-2 3B (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS500 (500 chains)
0.563 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DPLM-2 3B on TS500 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'DPLM-2 3B', column 'TS500' (page 17 of 21)
Configuration: HyInv default (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
0.382 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyInv on CATH4.2 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'HyInv', column 'CATH4.2 test' (page 17 of 21)
Configuration: HyInv default (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
0.373 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyInv on CATH4.3 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'HyInv', column 'CATH4.3 test' (page 17 of 21)
Configuration: HyInv default (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.421 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyInv on RecentPDB (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'HyInv', column 'RecentPDB' (page 17 of 21)
Configuration: HyInv default (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS50 (50 chains)
0.44 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyInv on TS50 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'HyInv', column 'TS50' (page 17 of 21)
Configuration: HyInv default (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS500 (500 chains)
0.458 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyInv on TS500 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'HyInv', column 'TS500' (page 17 of 21)
Configuration: LigandMPNN (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
0.427 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LigandMPNN on CATH4.2 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LigandMPNN', column 'CATH4.2 test' (page 17 of 21)
Configuration: LigandMPNN (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
0.411 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LigandMPNN on CATH4.3 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LigandMPNN', column 'CATH4.3 test' (page 17 of 21)
Configuration: LigandMPNN (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.453 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LigandMPNN on RecentPDB (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LigandMPNN', column 'RecentPDB' (page 17 of 21)
Configuration: LigandMPNN (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS50 (50 chains)
0.475 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LigandMPNN on TS50 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LigandMPNN', column 'TS50' (page 17 of 21)
Configuration: LigandMPNN (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS500 (500 chains)
0.511 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LigandMPNN on TS500 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LigandMPNN', column 'TS500' (page 17 of 21)
Configuration: LM-Design 650M (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.2 test (1,120 chains)
0.525 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LM-Design 650M on CATH4.2 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LM-Design 650M', column 'CATH4.2 test' (page 17 of 21)
Configuration: LM-Design 650M (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: CATH4.3 test (1,882 chains)
0.587 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LM-Design 650M on CATH4.3 test (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LM-Design 650M', column 'CATH4.3 test' (page 17 of 21)
Configuration: LM-Design 650M (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: RecentPDB (121 chains from 111 recent PDB entries)
0.516 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LM-Design 650M on RecentPDB (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LM-Design 650M', column 'RecentPDB' (page 17 of 21)
Configuration: LM-Design 650M (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS50 (50 chains)
0.601 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LM-Design 650M on TS50 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LM-Design 650M', column 'TS50' (page 17 of 21)
Configuration: LM-Design 650M (HyInv report)Protocol: Native sequence recovery of designed sequences (HyInv report)
Dataset: TS500 (500 chains)
0.634 Sequence recovery (Fraction of valid sites at which the design carries the native residue, averaged over the designs of a target and then over targets; descriptive in this report, with weight zero in HyInv's reward and no role in checkpoint selection)
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

LM-Design 650M on TS500 (Native sequence recovery of designed sequences, HyInv report)

hyinv-20261106-protocol-sequence-recovery

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 14, 'Recovery' block, row 'LM-Design 650M', column 'TS500' (page 17 of 21)

Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations
55

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-11-21-adc15377fab2. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

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

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

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

Technical metadata for this record is tracked under stable ID hyinv-20261106-protocol-sequence-recovery.

Source locator: Figure 14, 'Recovery' block; Appendix B 'Recovery'

Related records

Suggest a correction