Completeness and Diversity in Depth-First Proof-Number Search with Applications to Retrosynthesis
Authors: Christopher Franz, Georg Mogk, Thomas Mrziglod, Kevin Schewior
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In order to verify whether the MCTS and the DFPN* provide different quality levels in diversity, we performed computer experiments. 6 Experiments, Table 1: Comparison of MCTS and DFPN*. |
| Researcher Affiliation | Collaboration | Christopher Franz1 , Georg Mogk2 , Thomas Mrziglod2 and Kevin Schewior3 1Frankfurt, Germany 2Bayer AG, Leverkusen, Germany 3University of Southern Denmark, Odense, Denmark christopher@kotaico.de, {georg.mogk,thomas.mrziglod}@bayer.com, kevs@sdu.dk |
| Pseudocode | No | The paper describes algorithms in prose and mathematical notation but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include an unambiguous statement or link for the release of the authors' own source code for the described methodology. |
| Open Datasets | Yes | We analyze a sample data set consisting of 60 molecules1. ... 1available at https://doi.org/10.5281/zenodo.6511731 |
| Dataset Splits | No | The paper mentions a dataset of 60 molecules and another dataset of 31 million reactions used to train an ANN, but it does not specify any training, validation, or test dataset splits (e.g., percentages or sample counts) for reproducibility. |
| Hardware Specification | No | The paper states 'MCTS and DFPN* were each run on a single core' but provides no further specific details about the hardware (e.g., CPU or GPU models, memory specifications) used for the experiments. |
| Software Dependencies | No | The paper mentions using 'MLPDS' and 'an Artificial Neural Network' but does not provide specific version numbers for any software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | Constants such as Mpn and ε are set as in [Kishimoto et al., 2019] (Mpn = 20 and ε = 10 30). The only constant we changed is the threshold controlling parameter σ (they call it δ). Kishimoto et al. use σ = 2, whereas we set σ = 3... The penalties p AND and p OR from Section 4 were set to p AND = 10 and p OR = 0. In addition... maximum search depth... We set it to 7 and the maximum branching factor... to 50. For MCTS... the exploration constant was set to 2.0, the maximum depth to 7, and the maximum branching to 50. |