# Best feasible prompt identification on CNN/DailyMail (test)

Source: [Best feasible prompt identification on CNN/DailyMail (test)](<https://www.sota2.com/research/sota/best-feasible-prompt-identification-on-cnn-dailymail-test>)

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

Data updated: 2026-05-15T08:42:43.101Z

Evaluation of the ability to identify the best feasible prompt for text generation tasks using the CNN/DailyMail (test) dataset, measured by soft constrained reward metrics.

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 | Best feasible prompt identification |
| Dataset (including any stated split) | CNN/DailyMail (test) |
| Metric | Average Soft Constrained Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 72 of 72 |
| 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

- [Average Soft Constrained Reward](<https://www.sota2.com/research/sota/best-feasible-prompt-identification-on-cnn-dailymail-test.md?metric=Average%20Soft%20Constrained%20Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Average Soft Constrained Reward | Result date | Report paper |
| --- | --- | --- | --- |
| MLP-CSR | 0.172 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.167 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.166 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.165 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.164 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.164 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.163 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.162 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.161 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.161 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.16 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.16 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.16 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.16 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.157 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.157 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.155 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.155 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.154 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.154 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.154 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.154 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.154 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.153 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.153 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.151 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.148 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.146 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.144 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.142 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.142 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.138 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.138 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.136 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.134 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.134 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.126 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.123 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.091 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.088 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.081 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.072 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.062 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.045 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.045 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.044 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.032 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.032 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.032 | Not recorded | 6a06a87cdbc836b87d829f83 |
| MLP-CSR | 0.032 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.021 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.021 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.021 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.02 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.02 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.019 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.018 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.018 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.016 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.015 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.015 | Not recorded | 6a06a87cdbc836b87d829f83 |
| CSR | 0.015 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.015 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.01 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.008 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.008 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0.007 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0 | Not recorded | 6a06a87cdbc836b87d829f83 |
| Uniform | 0 | Not recorded | 6a06a87cdbc836b87d829f83 |

### MLP-CSR

Average Soft Constrained Reward: 0.172. Result ID: 6a06dc7447f34ce924ee8fb4.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"8"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.167. Result ID: 6a06dc7447f34ce924ee8fb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.166. Result ID: 6a06dc7447f34ce924ee8fa5.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.165. Result ID: 6a06dc7447f34ce924ee8fd5.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"10"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.164. Result ID: 6a06dc7447f34ce924ee8fa7.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"5"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.164. Result ID: 6a06dc7447f34ce924ee8fa8.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.163. Result ID: 6a06dc7447f34ce924ee8fa9.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"10"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.162. Result ID: 6a06dc7447f34ce924ee8fb3.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.161. Result ID: 6a06dc7447f34ce924ee8faf.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.161. Result ID: 6a06dc7447f34ce924ee8fb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.16. Result ID: 6a06dc7447f34ce924ee8fd8.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.16. Result ID: 6a06dc7447f34ce924ee8fd9.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.16. Result ID: 6a06dc7447f34ce924ee8fe1.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"10"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.16. Result ID: 6a06dc7447f34ce924ee8fe5.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.157. Result ID: 6a06dc7447f34ce924ee8fc6.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"3"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.157. Result ID: 6a06dc7447f34ce924ee8fd3.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.155. Result ID: 6a06dc7447f34ce924ee8fd4.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.155. Result ID: 6a06dc7447f34ce924ee8fd7.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.154. Result ID: 6a06dc7447f34ce924ee8fc9.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"10"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.154. Result ID: 6a06dc7447f34ce924ee8fcd.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.154. Result ID: 6a06dc7447f34ce924ee8fd2.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.154. Result ID: 6a06dc7447f34ce924ee8fe3.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"5"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.154. Result ID: 6a06dc7447f34ce924ee8fe4.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"8"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.153. Result ID: 6a06dc7447f34ce924ee8fa4.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.153. Result ID: 6a06dc7447f34ce924ee8fb5.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.151. Result ID: 6a06dc7447f34ce924ee8fe0.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"8"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.148. Result ID: 6a06dc7447f34ce924ee8fc8.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.146. Result ID: 6a06dc7447f34ce924ee8fb2.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.144. Result ID: 6a06dc7447f34ce924ee8fd6.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.142. Result ID: 6a06dc7447f34ce924ee8fca.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.142. Result ID: 6a06dc7447f34ce924ee8fcc.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"8"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.138. Result ID: 6a06dc7447f34ce924ee8fa6.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"3"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.138. Result ID: 6a06dc7447f34ce924ee8fdf.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.136. Result ID: 6a06dc7447f34ce924ee8fc7.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.134. Result ID: 6a06dc7447f34ce924ee8fa3.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"5"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.134. Result ID: 6a06dc7447f34ce924ee8fe2.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.126. Result ID: 6a06dc7447f34ce924ee8fcb.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.123. Result ID: 6a06dc7447f34ce924ee8fde.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"3"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.091. Result ID: 6a06dc7447f34ce924ee8fae.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"3"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.088. Result ID: 6a06dc7447f34ce924ee8fba.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"3"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.081. Result ID: 6a06dc7447f34ce924ee8fa2.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.072. Result ID: 6a06dc7447f34ce924ee8fc1.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.062. Result ID: 6a06dc7447f34ce924ee8fbc.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.045. Result ID: 6a06dc7447f34ce924ee8fb7.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"5"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.045. Result ID: 6a06dc7447f34ce924ee8fbf.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"5"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.044. Result ID: 6a06dc7447f34ce924ee8fdb.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"5"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.032. Result ID: 6a06dc7447f34ce924ee8f9f.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"5"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.032. Result ID: 6a06dc7447f34ce924ee8fbd.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"10"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.032. Result ID: 6a06dc7447f34ce924ee8fbe.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"3"}. This record does not assert independent reproduction.

### MLP-CSR

Average Soft Constrained Reward: 0.032. Result ID: 6a06dc7447f34ce924ee8fc0.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.021. Result ID: 6a06dc7447f34ce924ee8f9e.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"3"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.021. Result ID: 6a06dc7447f34ce924ee8fa0.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.021. Result ID: 6a06dc7447f34ce924ee8fa1.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"30","b":"10"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.02. Result ID: 6a06dc7447f34ce924ee8fab.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"5"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.02. Result ID: 6a06dc7447f34ce924ee8fac.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.019. Result ID: 6a06dc7447f34ce924ee8fda.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"3"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.018. Result ID: 6a06dc7447f34ce924ee8fdc.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.018. Result ID: 6a06dc7447f34ce924ee8fdd.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"100","b":"10"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.016. Result ID: 6a06dc7447f34ce924ee8fcf.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"5"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.015. Result ID: 6a06dc7447f34ce924ee8fb6.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"3"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.015. Result ID: 6a06dc7447f34ce924ee8fb9.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"10"}. This record does not assert independent reproduction.

### CSR

Average Soft Constrained Reward: 0.015. Result ID: 6a06dc7447f34ce924ee8fbb.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"5"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.015. Result ID: 6a06dc7447f34ce924ee8fce.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"3"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.01. Result ID: 6a06dc7447f34ce924ee8fd1.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"10"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.008. Result ID: 6a06dc7447f34ce924ee8fc4.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.008. Result ID: 6a06dc7447f34ce924ee8fd0.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"50","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0.007. Result ID: 6a06dc7447f34ce924ee8faa.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"3"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0. Result ID: 6a06dc7447f34ce924ee8fad.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"50","b":"10"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0. Result ID: 6a06dc7447f34ce924ee8fb8.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-7B","K":"100","b":"8"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0. Result ID: 6a06dc7447f34ce924ee8fc2.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"3"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0. Result ID: 6a06dc7447f34ce924ee8fc3.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"5"}. This record does not assert independent reproduction.

### Uniform

Average Soft Constrained Reward: 0. Result ID: 6a06dc7447f34ce924ee8fc5.

[Reporting paper](<https://www.sota2.com/research/paper/6a06a87cdbc836b87d829f83.md>)

Recorded evaluation configuration: {"Backbone":"Llama3-8B","K":"30","b":"10"}. This record does not assert independent reproduction.

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