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.
Online Selective Classification with Limited Feedback
Authors: Aditya Gangrade, Anil Kag, Ashok Cutkosky, Venkatesh Saligrama
NeurIPS 2021 | Venue PDF | LLM Run Details | Input Tokens: 19,664 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,504 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 | The theoretical exploration is complemented by illustrative experiments that implement our scheme on two benchmark datasets. We evaluate the performance of Algorithm 2 on two tasks CIFAR 10 [KH09], and GAS [Ver+12] see E for details of implementation, and here for the relevant code. |
| Researcher Affiliation | Academia | Aditya Gangrade Boston University EMAIL Anil Kag Boston University EMAIL Ashok Cutkosky Boston University EMAIL Venkatesh Saligrama Boston University EMAIL |
| Pseudocode | Yes | Algorithm 1 VUE |
| Open Source Code | Yes | code to reproduce the same is made available at https://github.com/anilkagak2/Online-Selective-Classification |
| Open Datasets | Yes | We evaluate the performance of Algorithm 2 on two tasks CIFAR 10 [KH09], and GAS [Ver+12] |
| Dataset Splits | No | No explicit statement detailing specific training/validation/test dataset splits (e.g., percentages, sample counts, or explicit standard split citations) was found. It mentions using a 'training set' and 'test datasets' but lacks specific split information. |
| Hardware Specification | No | No specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running the experiments are mentioned in the provided text. |
| Software Dependencies | No | No specific software dependencies with version numbers (e.g., 'Python 3.8, PyTorch 1.9') are explicitly mentioned in the provided text. |
| Experiment Setup | Yes | The hyperparameters (ยต, t) provide control over various levels of accuracy and abstention. Concretely, we vary these linearly for 20 values of p [0.015, 0.285], and 10 values of ฮต [0.001, 0.046]. |