SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.02383 · 2024

A Fresh Look at Sanity Checks for Saliency Maps

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
annahedstroem/sanity-checks-revisited canonical 3 of 5
FunctionStatusWhere it lives
create_feature_mask Ran annahedstroem/sanity-checks-revisited/src/utils.py
pointer only (licence: NONE) · get_code("0f255cbb9994459f")
create_masks_for_dataset Ran annahedstroem/sanity-checks-revisited/src/utils.py
pointer only (licence: NONE) · get_code("aa9a4b01e30326bb")
get_indices Ran annahedstroem/sanity-checks-revisited/src/utils.py
pointer only (licence: NONE) · get_code("ff4ec37fbb224c87")
get_dataloader Not yet run annahedstroem/sanity-checks-revisited/src/setup_models_datasets.py
pointer only (licence: NONE) · get_code("e37b2bec1c653a0e")
get_model Not yet run annahedstroem/sanity-checks-revisited/src/setup_models_datasets.py
pointer only (licence: NONE) · get_code("83d9e05e055c11eb")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The Model Parameter Randomisation Test (MPRT) is highly recognised in the eXplainable Artificial Intelligence (XAI) community due to its fundamental evaluative criterion: explanations should be sensitive to the parameters of the model they seek to explain. However, recent studies have raised several methodological concerns for the empirical interpretation of MPRT. In response, we propose two modifications to the original test: Smooth MPRT and Efficient MPRT. The former reduces the impact of noise on evaluation outcomes via sampling, while the latter avoids the need for biased similarity measurements by re-interpreting the test through the increase in explanation complexity after full model randomisation. Our experiments show that these modifications enhance the metric reliability, facilitating a more trustworthy deployment of explanation methods.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.02383")
get_code_for_paper("2405.02383")
have("2405.02383")

Connect an agent — have() is free.