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 |
|---|---|---|
| degesim/chep23deeptreegan | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| contains_nans | Ran | degesim/chep23deeptreegan/fgsim/utils/check_model.py pointer only (licence: NONE) · get_code("80d18d5b1ce63f6d") |
| format_layer_labels | Ran | degesim/chep23deeptreegan/fgsim/plot/modelgrads.py pointer only (licence: NONE) · get_code("65534e974b14c07c") |
| get_grad_dict | Ran | degesim/chep23deeptreegan/fgsim/plot/modelgrads.py pointer only (licence: NONE) · get_code("98ae7935e77d7f24") |
| import_nn | Ran | degesim/chep23deeptreegan/fgsim/ml/network.py pointer only (licence: NONE) · get_code("9fe3bf0b9eac5b4e") |
| is_anormal_tensor | Ran | degesim/chep23deeptreegan/fgsim/utils/check_model.py pointer only (licence: NONE) · get_code("ad418fbe47c4a937") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, the generation of large point clouds in a short time is required, while the complex dependencies between the particles must be correctly modelled. Particle showers are inherently tree-based processes, as each particle is produced by the decay or detector interaction of a particle of the previous generation. In this work, we present a novel Graph Neural Network model (DeepTreeGAN) that is able to generate such point clouds in a tree-based manner. We show that this model can reproduce complex distributions, and we evaluate its performance on the public JetNet dataset.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.12616")
get_code_for_paper("2311.12616")
have("2311.12616")
Connect an agent — have() is free.