We lifted 8 functions out of this paper's own repositories and ran 6 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 |
|---|---|---|
| andreartelt/diversesemifactualsreject | canonical | 6 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| check_rejections | Ran | andreartelt/diversesemifactualsreject/Implementation/modelselection.py code served (permissive licence) · get_code("42028523a1510c02") |
| evaluate_closeness | Ran | andreartelt/diversesemifactualsreject/Implementation/utils.py code served (permissive licence) · get_code("bc4c5c9d5c61353f") |
| find_nearest | Ran | andreartelt/diversesemifactualsreject/Implementation/modelselection.py code served (permissive licence) · get_code("579fa0d53f14ed26") |
| generate_model | Ran | andreartelt/diversesemifactualsreject/Implementation/modelselection_conformal.py code served (permissive licence) · get_code("263f6e7d29c9126d") |
| get_model | Ran | andreartelt/diversesemifactualsreject/Implementation/experiments.py code served (permissive licence) · get_code("99a5c1962499e9e2") |
| rate_of_lists | Ran | andreartelt/diversesemifactualsreject/Implementation/modelselection.py code served (permissive licence) · get_code("fbe4bae359ba8d8d") |
| evaluate_sparsity | Not yet run | andreartelt/diversesemifactualsreject/Implementation/utils.py code served (permissive licence) · get_code("c5281a154e61faf7") |
| get_model_parameters | Not yet run | andreartelt/diversesemifactualsreject/Implementation/experiments.py code served (permissive licence) · get_code("732ea5fb7eb1330f") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Machine learning based decision making systems applied in safety critical areas require reliable high certainty predictions. For this purpose, the system can be extended by an reject option which allows the system to reject inputs where only a prediction with an unacceptably low certainty would be possible. While being able to reject uncertain samples is important, it is also of importance to be able to explain why a particular sample was rejected. With the ongoing rise of eXplainable AI (XAI), a lot of explanation methodologies for machine learning based systems have been developed -- explaining reject options, however, is still a novel field where only very little prior work exists. In this work, we propose to explain rejects by semifactual explanations, an instance of example-based explanation methods, which them self have not been widely considered in the XAI community yet. We propose a conceptual modeling of semifactual explanations for arbitrary reject options and empirically evaluate a specific implementation on a conformal prediction based reject option.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.01898")
get_code_for_paper("2207.01898")
have("2207.01898")
Connect an agent — have() is free.