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..
Small Representations of Big Kidney Exchange Graphs
Authors: John Dickerson, Aleksandr Kazachkov, Ariel Procaccia, Tuomas Sandholm
AAAI 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experiments show that, indeed, small numbers of attributes suffice. |
| Researcher Affiliation | Academia | University of Maryland Carnegie Mellon University |
| Pseudocode | Yes | Algorithm 1 L-CYCLE-COVER |
| Open Source Code | No | Code for this section will be made available once the double-blind period is over; the code itself uniquely identifies the authors. |
| Open Datasets | No | The paper uses "real compatibility graphs from the UNOS US-wide kidney exchange" and "real match run data from the first two years of the United Network for Organ Sharing (UNOS) kidney exchange" but does not provide a specific link, DOI, or formal citation for accessing this exact dataset for reproducibility. |
| Dataset Splits | No | The paper does not specify exact split percentages, absolute sample counts, or reference predefined splits with citations for training, validation, or test data. |
| Hardware Specification | Yes | with access to 16GB of RAM, 4 cores, and 60 minutes of wall time. |
| Software Dependencies | No | The paper mentions "a SAT solver (Biere 2014)" and "a leading commercial ILP solver (IBM ILOG Inc 2015)" but does not provide specific version numbers for these software dependencies. |
| Experiment Setup | No | The paper describes mathematical programming formulations and solver limits (e.g., '60 minutes of wall time') but does not provide specific hyperparameter values or detailed training configurations for any model. |