EditJumps section 4.2 frame, 200 references: KL pool.
Kullback-Leibler divergence between the pooled amino-acid composition of the generated set and that of the natural reference set. Computed under the paper's section 4.2 frame: 20 templates and 20 variants per template against a 200-sequence held-out natural homolog set.
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.
12 recorded evaluations, 12 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
12 evaluations · 12 results. Different protocols are not a single leaderboard.
Protocol: EditJumps section 4.2 frame, 200 references: KL pool.
Sorted by Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) (lower 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.
All 12 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: EditJumps editor, clock normalisation 40 | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: HER2-VH reference holdout, 200 homologs | 0.63 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEditJumps on HER2-VH, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "her2vh", row "EditJumps", column "KL pool." |
| Configuration: EditJumps editor, clock normalisation 40 | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: Ty1 reference holdout, 200 homologs | 0.5 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEditJumps on Ty1, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "EditJumps", column "KL pool." |
| Configuration: EvoDiff-MSA under a matched mutation budget | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: HER2-VH reference holdout, 200 homologs | 0.42 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEvoDiff on HER2-VH, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "her2vh", row "EvoDiff", column "KL pool." |
| Configuration: EvoDiff-MSA under a matched mutation budget | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: Ty1 reference holdout, 200 homologs | 0.61 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEvoDiff on Ty1, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "EvoDiff", column "KL pool." |
| Configuration: Evotuned ESM-2 650M, forced substitution | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: HER2-VH reference holdout, 200 homologs | 0.59 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEvotune-f on HER2-VH, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "her2vh", row "Evotune-f", column "KL pool." |
| Configuration: Evotuned ESM-2 650M, forced substitution | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: Ty1 reference holdout, 200 homologs | 0.53 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEvotune-f on Ty1, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "Evotune-f", column "KL pool." |
| Configuration: Evotuned ESM-2 650M, unforced infilling | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: HER2-VH reference holdout, 200 homologs | 0.37 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEvotune on HER2-VH, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "her2vh", row "Evotune", column "KL pool." |
| Configuration: Evotuned ESM-2 650M, unforced infilling | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: Ty1 reference holdout, 200 homologs | 0.54 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEvotune on Ty1, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "Evotune", column "KL pool." |
| Configuration: Random mutation floor | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: HER2-VH reference holdout, 200 homologs | 0.79 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcerand. mut. on HER2-VH, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "her2vh", row "rand. mut.", column "KL pool." |
| Configuration: Random mutation floor | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: Ty1 reference holdout, 200 homologs | 0.77 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcerand. mut. on Ty1, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "rand. mut.", column "KL pool." |
| Configuration: Random homolog pairing ceiling | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: HER2-VH reference holdout, 200 homologs | 0.1 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcerand. pair. on HER2-VH, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "her2vh", row "rand. pair.", column "KL pool." |
| Configuration: Random homolog pairing ceiling | Protocol: EditJumps section 4.2 frame, 200 references: KL pool. Dataset subset: Ty1 reference holdout, 200 homologs | 0.14 Kullback leibler divergence (pooled amino-acid composition against a 200-sequence natural holdout) unitless · lower Uncertainty: Not reported by the source: The table prints a single value with no interval. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcerand. pair. on Ty1, KL pool., 200 references One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence. Aggregation: Not reported When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "rand. pair.", column "KL pool." |
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.
- EditJumps on HER2-VH, KL pool., 200 references
- EditJumps on Ty1, KL pool., 200 references
- EvoDiff on HER2-VH, KL pool., 200 references
- EvoDiff on Ty1, KL pool., 200 references
- Evotune-f on HER2-VH, KL pool., 200 references
- Evotune-f on Ty1, KL pool., 200 references
- Evotune on HER2-VH, KL pool., 200 references
- Evotune on Ty1, KL pool., 200 references
- rand. mut. on HER2-VH, KL pool., 200 references
- rand. mut. on Ty1, KL pool., 200 references
- rand. pair. on HER2-VH, KL pool., 200 references
- rand. pair. on Ty1, KL pool., 200 references
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
- 12
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
| Property and statement | Original source and location | Review 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 history
- When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Original source · arXiv:2609.18745v1, 16 September 2026
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID editjumps-20261115-protocol-ours-200-kl-pooled.
Related records
- evaluates task: Homolog-like variant generation from a seed antibody sequence
- assessment: EditJumps on HER2-VH, KL pool., 200 references
- assessment: EditJumps on Ty1, KL pool., 200 references
- assessment: EvoDiff on HER2-VH, KL pool., 200 references
- assessment: EvoDiff on Ty1, KL pool., 200 references
- assessment: Evotune-f on HER2-VH, KL pool., 200 references
- assessment: Evotune-f on Ty1, KL pool., 200 references
- assessment: Evotune on HER2-VH, KL pool., 200 references
- assessment: Evotune on Ty1, KL pool., 200 references
- assessment: rand. mut. on HER2-VH, KL pool., 200 references
- assessment: rand. mut. on Ty1, KL pool., 200 references
- assessment: rand. pair. on HER2-VH, KL pool., 200 references
- assessment: rand. pair. on Ty1, KL pool., 200 references