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..
How Patterns Dictate Learnability in Sequential Data
Authors: Mario Morawski, Anaïs Després, Remi Rehm
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We validate our framework through experiments on synthetic data, demonstrating its ability to assess model adequacy, quantify the inherent complexity of a dataset, and reveal interpretable structure in sequential data. |
| Researcher Affiliation | Academia | Mario Morawski Anaïs Després |
| Pseudocode | Yes | Algorithm 1 Ipred: Data is sampled in a sequential manner with temporal alignment |
| Open Source Code | Yes | The codes are available on Git Hub: https://github.com/EkMeasurable/Learnability_Ipred |
| Open Datasets | No | The paper primarily uses synthetic data (Gaussian process, autoregressive process, Ising Spin Sequences) generated by the authors, for which explicit public access information is not provided. While it mentions the 'Exchange dataset from Gluon Ts [1]', it cites the GluonTS library paper (Alexandrov et al., 2020) and not a direct source or formal citation for the dataset itself. |
| Dataset Splits | Yes | The dataset is split into 80% training and 20% validation sets, and results are averaged across runs to account for variance. |
| Hardware Specification | Yes | All experiments were conducted on a system equipped with a 14-core CPU, a 20-core integrated GPU, 24 GB of unified memory, and 1 TB of SSD storage. |
| Software Dependencies | No | The paper mentions software components like 'Adam optimizer', 'MLP', 'LSTM', and variational estimators 'SMILE', 'NWJ', 'Info NCE', 'TUBA', 'DV', but does not provide specific version numbers for any of them. |
| Experiment Setup | Yes | Training is performed using the Adam optimizer with a learning rate of 10-3 and a batch size of 128. For each value of k, training proceeds for up to 1000 epochs, using early stopping with a patience of 10 epochs based on validation loss. |