Consolidated, deduplicated-by-question view of every APPS problem we have a
backdoored solution for. Built to support training and evaluating Llama-3.3-70B
as a backdoor detector / collusion monitor.
The unit of uniqueness is the APPS problem id (pid). The same problem
re-backdoored by a different model is treated as a duplicate question and
collapsed — repeating questions across train/eval is data contamination, so we
deduplicate at the question level… See the full description on the dataset page:
https://huggingface.co/datasets/jprivera44/collusion-project-apps-backdoor-inventory.
