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..
Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence
Authors: Yancheng Huang, Kai Yang, Zelin Zhu, Leian Chen
ICML 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments have been conducted to elucidate the effectiveness of the proposed method. |
| Researcher Affiliation | Academia | 1Tongji University 2Columbia University 3This work was done prior to Leian Chen joining Amazon. |
| Pseudocode | Yes | Algorithm 1 Triadic-OCD |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | In our experiments, we utilized the measurement data generated from the IEEE-14 bus power system, which can be regarded as a benchmark dataset in current research studies. |
| Dataset Splits | No | The paper mentions using the IEEE-14 bus power system dataset but does not specify any training, validation, or test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used to conduct the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with their version numbers, which would be necessary for reproducibility. |
| Experiment Setup | Yes | In our experiment, we assume that the system matrix can be accurately determined in all areas except for the 4th area. Suppose attackers utilize a sequence of randomly generated fabricated vectors to compromise the meter reading y(t) from the time instant ta. The generation process of the injected attacks is as follows, a(t) = P Hu, ui U(0.1, 1), where P H I H HT H 1 HT . Given the fluctuations in admittance caused by factors like environmental disturbances, the detection algorithms employed in the experiment utilize imprecise estimates of H to identify anomaly vectors injected into smart grid systems. We provide the inaccurate estimates of H in Appendix A, as well as the corresponding detailed settings of various uncertainty sets. |