diff --git a/examples/a.py b/examples/a.py
deleted file mode 100644
index 94c7478..0000000
--- a/examples/a.py
+++ /dev/null
@@ -1,27 +0,0 @@
-import jax
-from jax import numpy as jnp
-
-from config import Config
-from core import Genome
-
-config = Config()
-from dataclasses import asdict
-
-print(asdict(config))
-
-pop_nodes = jnp.ones((Config.basic.pop_size, Config.neat.maximum_nodes, 3))
-pop_conns = jnp.ones((Config.basic.pop_size, Config.neat.maximum_conns, 5))
-
-pop_genomes = Genome(pop_nodes, pop_conns)
-
-print(pop_genomes)
-print(pop_genomes[0: 20])
-
-@jax.vmap
-def pop_cnts(genome):
-    return genome.count()
-
-cnts = pop_cnts(pop_genomes)
-
-print(cnts)
-
diff --git a/examples/b.py b/examples/b.py
deleted file mode 100644
index deb7808..0000000
--- a/examples/b.py
+++ /dev/null
@@ -1,23 +0,0 @@
-from enum import Enum
-from jax import jit
-
-class NetworkType(Enum):
-    ANN = 0
-    SNN = 1
-    LSTM = 2
-
-
-
-
-@jit
-def func(d):
-    return d[0] + 1
-
-
-d = {0: 1, 1: NetworkType.ANN.value}
-n = None
-
-print(n or d)
-print(d)
-
-print(func(d))
diff --git a/examples/xor.py b/examples/xor.py
index c6d6236..18afeef 100644
--- a/examples/xor.py
+++ b/examples/xor.py
@@ -27,8 +27,8 @@ if __name__ == '__main__':
             pop_size=10000
         ),
         neat=NeatConfig(
-            maximum_nodes=50,
-            maximum_conns=100,
+            maximum_nodes=20,
+            maximum_conns=50,
         ),
         gene=NormalGeneConfig()
     )
diff --git a/paper.txt b/paper.txt
deleted file mode 100644
index ae0b224..0000000
--- a/paper.txt
+++ /dev/null
@@ -1,37 +0,0 @@
-Abstract
-Neuroevolution is a subfield of artificial intelligence that
-leverages evolutionary algorithms to generate and optimize
-artificial neural networks. This technique has proven to be
-successful in solving a wide range of complex problems
-across various domains. The NeuroEvolution of Augmenting
-Topologies (NEAT) is one of the most renowned algorithms
-in neuroevolution. Characterized by its openendedness, it
-starts with minimal networks and progressively evolves both
-the topology and the weights of these networks to optimize
-performance. However, the acceleration techniques employed
-in prevailing NEAT implementations typically rely on par-
-allelism on CPUs, failing to harness the rapidly expand-
-ing computational resources of today. To bridge this gap,
-we present NEATAX, an innovative framework that adapts
-NEAT for execution on hardware accelerators. Built on top
-of the JAX, NEATAX represents networks with varying topo-
-logical structures as tensors with the common shape, facili-
-tating efficient parallel computation using function vectoriza-
-tion. Upon rigorous testing across various tasks, we found
-that NEATAX has the capacity to shrink the computa-
-tion time from hours or even days down to a matter of
-minutes. These results demonstrate the potential of NEATAX
-as a scalable and efficient solution for neuroevolution tasks,
-paving the way for the future application of NEAT in more
-complex and demanding scenarios. NEATAX is available at
-https://github.com/WLS2002/neatax
-
-\section{Introduction}
-
-Inspired by the principles of natural selection and genetic inheritance, Evolutionary Computation (EC) has emerged
-as a powerful approach in the field of Artificial Intelligence (AI). EC exhibits a robust ability to explore vast
-and complex solution spaces, which is particularly critical when tackling ``black box" optimization problems where the
-internal structure isn't fully visible or understood. Leveraging the power of population-based search, EC navigates
-these complexities to arrive at near-optimal solutions \cite{eiben2015introduction}. However, despite these strengths, recent scholarship has
-highlighted limitations of EC. Important aspects such as ``openendedness" and ``genotype-to-phenotype mappings" warrant
-further attention, especially in light of EC's tendency to rely on small populations and strong selection pressure \cite{miikkulainen_biological_2021}.