SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.15965 · 2023

TraCE: Trajectory Counterfactual Explanation Scores

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 9 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
jeffnclark/trace canonical 9 of 14
FunctionStatusWhere it lives
change_categorical Ran jeffnclark/trace/helpers/funcs_icu_study.py
code served (permissive licence) · get_code("0ce50857b146ff6e")
cos_sim Ran jeffnclark/trace/helpers/funcs.py
code served (permissive licence) · get_code("bff9357caec21792")
n_sphere Ran jeffnclark/trace/helpers/funcs.py
code served (permissive licence) · get_code("9c7a8779b32dbd02")
nan_post_processing_data Ran jeffnclark/trace/helpers/funcs_icu_study.py
code served (permissive licence) · get_code("8dcf34339f3961ce")
obtain_stay_id_individuals Ran jeffnclark/trace/ICU_TraCE_scores.py
code served (permissive licence) · get_code("51e1fcbf1e618076")
plot_dataset Ran jeffnclark/trace/helpers/plotters.py
code served (permissive licence) · get_code("f6e80cda9b180e6d")
plot_decision_boundary Ran jeffnclark/trace/helpers/plotters.py
code served (permissive licence) · get_code("bb274893d5e95c1a")
plot_density Ran jeffnclark/trace/helpers/plotters.py
code served (permissive licence) · get_code("6377a0fb1f97b336")
vec Ran jeffnclark/trace/helpers/funcs.py
code served (permissive licence) · get_code("ffa2aada7cc61d14")
cf_generator Not yet run jeffnclark/trace/helpers/funcs_icu_study.py
code served (permissive licence) · get_code("ecef3ab232914eb3")
convert_nc_to_csv Not yet run jeffnclark/trace/helpers/funcs_ssp_study.py
code served (permissive licence) · get_code("e31cd68943331ac1")
generate_dice_cf_global Not yet run jeffnclark/trace/ICU_TraCE_scores.py
code served (permissive licence) · get_code("9d32e662b0e911b9")
merge_exp_versions Not yet run jeffnclark/trace/helpers/funcs_ssp_study.py
code served (permissive licence) · get_code("53fb628bd87a789a")
train_classifier Not yet run jeffnclark/trace/ICU_TraCE_scores.py
code served (permissive licence) · get_code("2080bccdc34c542c")

Repositories linked to this paper

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

Abstract

Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box classifier. In this paper, we propose to extend the use of counterfactuals to evaluate progress in sequential decision making tasks. To this end, we introduce a model-agnostic modular framework, TraCE (Trajectory Counterfactual Explanation) scores, which is able to distill and condense progress in highly complex scenarios into a single value. We demonstrate TraCE's utility across domains by showcasing its main properties in two case studies spanning healthcare and climate change.

For agents

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

get_harvested_code_for_paper("2309.15965")
get_code_for_paper("2309.15965")
have("2309.15965")

Connect an agent — have() is free.