# LTL Property Verification on Grid-world environment

Source: [LTL Property Verification on Grid-world environment](<https://www.sota2.com/research/sota/ltl-property-verification-on-grid-world-environment>)

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

Data updated: 2026-06-01T10:28:10.518Z

Evaluation of LTL Property Verification performance within the Grid-world environment, measured by certificate validity and PRISM satisfaction probability.

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 | LTL Property Verification |
| Dataset (including any stated split) | Grid-world environment |
| Metric | PRISM Satisfaction Probability |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [PRISM Satisfaction Probability](<https://www.sota2.com/research/sota/ltl-property-verification-on-grid-world-environment.md?metric=PRISM%20Satisfaction%20Probability>): Higher is better; unit: PERCENT.

- [Valid Certificates](<https://www.sota2.com/research/sota/ltl-property-verification-on-grid-world-environment.md?metric=Valid%20Certificates>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PRISM Satisfaction Probability | Result date | Report paper |
| --- | --- | --- | --- |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 100 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 83.33 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 45.32 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 21.69 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 17.6 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 10.51 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 7.71 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 7.39 | Not recorded | 6a1d123cdbd7150506f841ea |
| Theorem 2 reward design | 2.07 | Not recorded | 6a1d123cdbd7150506f841ea |

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c1743fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"F b","DSA states":"2","Streett pairs":"1","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c1743fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"F b ∧ G ¬h","DSA states":"3","Streett pairs":"1","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c1743fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"FG e ∧ G ¬h","DSA states":"3","Streett pairs":"2","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c174400.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF b","DSA states":"2","Streett pairs":"1","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c174402.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF a ∧ GF b ∧ G ¬h","DSA states":"6","Streett pairs":"1","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c174404.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF (a ∨ b) → FG ¬e","DSA states":"7","Streett pairs":"2","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c174406.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"F (c ∧ F (d ∧ GF a ∧ GF b)) ∧ G ¬h","DSA states":"6","Streett pairs":"1","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 100. Result ID: 6a1d5eb6fbc373592c174408.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF a → GF (b ∨ c)","DSA states":"3","Streett pairs":"1","Policy type":"Satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 83.33. Result ID: 6a1d5eb6fbc373592c174403.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF a ∧ GF b ∧ G ¬h","DSA states":"6","Streett pairs":"1","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 45.32. Result ID: 6a1d5eb6fbc373592c1743fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"F b ∧ G ¬h","DSA states":"3","Streett pairs":"1","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 21.69. Result ID: 6a1d5eb6fbc373592c174401.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF b","DSA states":"2","Streett pairs":"1","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 17.6. Result ID: 6a1d5eb6fbc373592c1743fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"F b","DSA states":"2","Streett pairs":"1","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 10.51. Result ID: 6a1d5eb6fbc373592c1743ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"FG e ∧ G ¬h","DSA states":"3","Streett pairs":"2","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 7.71. Result ID: 6a1d5eb6fbc373592c174407.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"F (c ∧ F (d ∧ GF a ∧ GF b)) ∧ G ¬h","DSA states":"6","Streett pairs":"1","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 7.39. Result ID: 6a1d5eb6fbc373592c174409.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF a → GF (b ∨ c)","DSA states":"3","Streett pairs":"1","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

### Theorem 2 reward design

PRISM Satisfaction Probability: 2.07. Result ID: 6a1d5eb6fbc373592c174405.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d123cdbd7150506f841ea.md>)

Recorded evaluation configuration: {"Specification":"GF (a ∨ b) → FG ¬e","DSA states":"7","Streett pairs":"2","Policy type":"Non-satisfying"}. This record does not assert independent reproduction.

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