Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Computing Superior Counter-Examples for Conformant Planning
Authors: Xiaodi Zhang, Alban Grastien, Enrico Scala10017-10024
AAAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The empirical experiments validate our approach. Section 6 presents an empirical evaluation. |
| Researcher Affiliation | Academia | 1Research School of Computer Science, Australian National University, Canberra 2Universit a degli Studi di Brescia |
| Pseudocode | Yes | Algorithm 1 The conformant planner g CPCES. Algorithm 2 compute-optimal-counterexample: ( indicates that there is no solution). |
| Open Source Code | Yes | The source code and the benchmarks are available at this address: bitbucket.org/enricode/cpces/. |
| Open Datasets | Yes | The source code and the benchmarks are available at this address: bitbucket.org/enricode/cpces/. |
| Dataset Splits | No | The paper refers to existing benchmark domains but does not specify explicit training, validation, or test dataset splits. |
| Hardware Specification | No | Experiments were run on Ubuntu with 16GB memory on a 3.6GHz CPU. |
| Software Dependencies | No | In particular we used the same underlying classical planner FF (Hoffmann and Nebel 2001) and the SAT solver Z3 (de Moura and Bjørner 2008). |
| Experiment Setup | No | Timeout was set to 3600 secs. |