# Randomized Reductions Discovery on RSR-Bench

Source: [Randomized Reductions Discovery on RSR-Bench](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-01T07:04:10.679Z

Evaluation of the ability to discover randomized reductions using the RSR-Bench dataset, focusing on property verification counts and runtime performance.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Randomized Reductions Discovery |
| Dataset (including any stated split) | RSR-Bench |
| Metric | RSR Count |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [RSR Count](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=RSR%20Count>): Higher is better; unit: SCALAR.

- [Verified Properties Count](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=Verified%20Properties%20Count>): Higher is better; unit: SCALAR.

- [Unverified Properties Count](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=Unverified%20Properties%20Count>): Lower is better; unit: SCALAR.

- [RSR Coverage](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=RSR%20Coverage>): Higher is better; unit: PERCENT.

- [Min Runtime (sec)](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=Min%20Runtime%20(sec)>): Lower is better; unit: TIME.

- [Average Runtime (sec)](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=Average%20Runtime%20(sec)>): Lower is better; unit: TIME.

- [Max Runtime (sec)](<https://www.sota2.com/research/sota/randomized-reductions-discovery-on-rsr-bench.md?metric=Max%20Runtime%20(sec)>): Lower is better; unit: TIME.

## Recorded results

| Method | RSR Count | Result date | Report paper |
| --- | --- | --- | --- |
| A-BITWEEN | 793 | Not recorded | 68fa7ba01e209131cea896d2 |
| A-BITWEEN | 293 | Not recorded | 68fa7ba01e209131cea896d2 |
| N-RESEARCH | 250 | Not recorded | 68fa7ba01e209131cea896d2 |
| N-RESEARCH | 191 | Not recorded | 68fa7ba01e209131cea896d2 |
| N-RESEARCH | 170 | Not recorded | 68fa7ba01e209131cea896d2 |
| A-BITWEEN | 157 | Not recorded | 68fa7ba01e209131cea896d2 |
| V-BITWEEN | 87 | Not recorded | 68fa7ba01e209131cea896d2 |
| V-BITWEEN | 74 | Not recorded | 68fa7ba01e209131cea896d2 |
| V-BITWEEN | 61 | Not recorded | 68fa7ba01e209131cea896d2 |
| V-BITWEEN | 48 | Not recorded | 68fa7ba01e209131cea896d2 |

### A-BITWEEN

RSR Count: 793. Result ID: 6a1d2e59fbc373592c15df2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"Claude-Opus-4.1"}. This record does not assert independent reproduction.

### A-BITWEEN

RSR Count: 293. Result ID: 6a1d2e59fbc373592c15df2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"Claude-Sonnet-4"}. This record does not assert independent reproduction.

### N-RESEARCH

RSR Count: 250. Result ID: 6a1d2e59fbc373592c15df28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"Claude-Opus-4.1"}. This record does not assert independent reproduction.

### N-RESEARCH

RSR Count: 191. Result ID: 6a1d2e59fbc373592c15df27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"Claude-Sonnet-4"}. This record does not assert independent reproduction.

### N-RESEARCH

RSR Count: 170. Result ID: 6a1d2e59fbc373592c15df26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"GPT-OSS-120B"}. This record does not assert independent reproduction.

### A-BITWEEN

RSR Count: 157. Result ID: 6a1d2e59fbc373592c15df29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"GPT-OSS-120B"}. This record does not assert independent reproduction.

### V-BITWEEN

RSR Count: 87. Result ID: 6a1d2e59fbc373592c15df25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"LR"}. This record does not assert independent reproduction.

### V-BITWEEN

RSR Count: 74. Result ID: 6a1d2e59fbc373592c15df24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"MILP"}. This record does not assert independent reproduction.

### V-BITWEEN

RSR Count: 61. Result ID: 6a1d2e59fbc373592c15df22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"PySR"}. This record does not assert independent reproduction.

### V-BITWEEN

RSR Count: 48. Result ID: 6a1d2e59fbc373592c15df23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896d2.md>)

Recorded evaluation configuration: {"Backend":"GPLearn"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.