SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.00454 · 2022

PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 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
abogatskiy/pelican canonical 9 of 13
FunctionStatusWhere it lives
batch_stack Ran abogatskiy/pelican/src/dataloaders/collate.py
code served (permissive licence) · get_code("24e331d34e433ea7")
batch_stack_general Ran abogatskiy/pelican/src/dataloaders/collate.py
code served (permissive licence) · get_code("10a3df87d5f15661")
dot4 Ran abogatskiy/pelican/src/layers/generic_layers.py
code served (permissive licence) · get_code("694761f75d833a17")
drop_zeros Ran abogatskiy/pelican/src/dataloaders/collate.py
code served (permissive licence) · get_code("722a984c73411427")
expand_var_list Ran abogatskiy/pelican/src/models/pelican_classifier.py
code served (permissive licence) · get_code("d9fc2929e852c9fa")
get_activation_fn Ran abogatskiy/pelican/src/layers/generic_layers.py
code served (permissive licence) · get_code("c3b4e5ac5f9963cc")
silu Ran abogatskiy/pelican/src/layers/generic_layers.py
code served (permissive licence) · get_code("f1b30721af3f5563")
suggest_params Ran abogatskiy/pelican/optuna_pelican_classifier.py
code served (permissive licence) · get_code("87aa69a0754cb533")
suggest_params Ran abogatskiy/pelican/optuna_pelican_cov.py
code served (permissive licence) · get_code("acd7554fd7e413e6")
add_pid_jc Not yet run abogatskiy/pelican/src/models/pelican_classifier.py
code served (permissive licence) · get_code("04cd63c8bd04eecf")
initialize_datasets Not yet run abogatskiy/pelican/src/dataloaders/utils.py
code served (permissive licence) · get_code("fda94d00076b72e0")
onehot Not yet run abogatskiy/pelican/src/models/pelican_cov.py
code served (permissive licence) · get_code("aac3499a7873a4b0")
qg_onehot Not yet run abogatskiy/pelican/src/models/pelican_classifier.py
code served (permissive licence) · get_code("4e1231b1e3c1a574")

Repositories linked to this paper

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

Abstract

Many current approaches to machine learning in particle physics use generic architectures that require large numbers of parameters and disregard underlying physics principles, limiting their applicability as scientific modeling tools. In this work, we present a machine learning architecture that uses a set of inputs maximally reduced with respect to the full 6-dimensional Lorentz symmetry, and is fully permutation-equivariant throughout. We study the application of this network architecture to the standard task of top quark tagging and show that the resulting network outperforms all existing competitors despite much lower model complexity. In addition, we present a Lorentz-covariant variant of the same network applied to a 4-momentum regression task.

For agents

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

get_harvested_code_for_paper("2211.00454")
get_code_for_paper("2211.00454")
have("2211.00454")

Connect an agent — have() is free.