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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
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. |