We lifted 5 functions out of this paper's own repositories and ran 5 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.
| Repository | Role | Ran |
|---|---|---|
| pair-code/what-if-tool | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| ensure_not_binary | Ran | pair-code/what-if-tool/utils/inference_utils.py code served (permissive licence) · get_code("c09d84260bbe1825") |
| filepath_to_filepath_list | Ran | pair-code/what-if-tool/utils/platform_utils.py code served (permissive licence) · get_code("8312c60a13f07762") |
| parse_original_feature_from_example | Ran | pair-code/what-if-tool/utils/inference_utils.py code served (permissive licence) · get_code("432d95cbff7f6c50") |
| path_is_parent | Ran | pair-code/what-if-tool/utils/platform_utils.py code served (permissive licence) · get_code("02df712a578b5861") |
| proto_value_for_feature | Ran | pair-code/what-if-tool/utils/inference_utils.py code served (permissive licence) · get_code("e07682087b90dcf9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners to probe, visualize, and analyze ML systems, with minimal coding. The What-If Tool lets practitioners test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data. It also lets practitioners measure systems according to multiple ML fairness metrics. We describe the design of the tool, and report on real-life usage at different organizations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1907.04135")
get_code_for_paper("1907.04135")
have("1907.04135")
Connect an agent — have() is free.