Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Compositional Neural Logic Programming
Authors: Son N. Tran
IJCAI 2021 | Venue PDF | LLM Run Details | Input Tokens: 16,999 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,855 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In the experiments, we demonstrate the advantages of CNLP in discriminative tasks and generative tasks. and 4 Experiments section with subsections like 4.1 Comparison KB, 4.2 Addition, 4.3 Semantic Image Interpretation where performance metrics and comparisons are provided. |
| Researcher Affiliation | Academia | Son N. Tran University of Tasmania EMAIL |
| Pseudocode | Yes | Algorithm 1 Voting Backward-Forward Chaining (sketch) |
| Open Source Code | No | The paper does not provide concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described in this paper. |
| Open Datasets | Yes | 10000 digit images and their labels are extracted from the MNIST dataset1 as the facts for the digit predicate. and http://yann.lecun.com/exdb/mnist/ |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning. |
| Hardware Specification | Yes | We run 1000 queries for the addition(*,*,?) task using a computer with a quad-core 3.6 GHz CPU and 16 GB of RAM. |
| Software Dependencies | No | The paper mentions 'Adam optimizer' but does not provide specific ancillary software details like library or framework names with version numbers (e.g., Python 3.x, PyTorch 1.x). |
| Experiment Setup | Yes | All models were trained by Adam optimizer with the batch size 64. and For a fair comparison, we also use the RMSProp optimiser for training as in [Donadello et al., 2017]. |