SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.13705 · ICML · 2024

A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data

Yanjie Li, Min Wu, Wenqiang Li, Weijun Li, Lina Yu, Linjun Sun, Jingyi Liu, Shu Wei, Yusong Deng, Meilan Hao

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 4 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2309.13705.json · badge: /api/ran/2309.13705.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ailwq/dysymnet canonical (classifier label)
classifier basis: classifier_2025
6 ran · 4 no recorded run
trevorstephens/gplearn canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Agent Ran
ran on a synthesized input · constructed an object; no result was computed
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("dfa37a557d19c715")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, Agent: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

ARGS = {
    'auto': True,
    'input_size': 4,
    'hidden_size': 8,
    'num_funcs_avail': 5,
    'n_layers': [2, 3, 4],
    'num_funcs_layer': [1, 2],
    'device': 'cpu',
    'dtype': torch.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Agent — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Agent output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
L12Smooth Ran
ran on a synthesized input · constructed an object; no result was computed
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("1d0f2f5241b1a2e0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, L12Smooth: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

ARGS = {
    "a": 0.05
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type L12Smooth — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a L12Smooth output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
R_Square Ran
ran; our contract draft was wrong, not the code
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("6a982d40b682d132")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create sample data for R_Square function
# y and y_pred should be same shape (num_samples,) or (num_samples, 1)
# Using shape (2,) for num_samples=2
y = torch.tensor([1.0, 2.0])
y_pred = torch.tensor([1.1, 1.9])

ARGS = {
    "y": y,
    "y_pred": y_pred
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
TimedFun Ran
ran on a synthesized input · constructed an object; no result was computed
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("0dd06e394743c8f6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, TimedFun: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import time

torch.manual_seed(0)

# Define a simple function to pass to TimedFun
def simple_function(x, y=None):
    """A simple function that takes x and optional y"""
    result = x * 2
    if y is not None:
        result = result + y
    return result

# Define ARGS dictionary with all parameters for TimedFun
ARGS = {
    'fun': simple_function,
    'stop_after': 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TimedFun — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TimedFun output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
check_random_state Ran
ran; our contract draft was wrong, not the code
trevorstephens/gplearn/gplearn/utils.py
code served (permissive licence) · get_code("3fa9926cc2520c35")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned RandomState. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numbers
import numpy as np

ARGS = {
    'seed': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RandomState — a RandomState output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RandomState output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_data Ran
ran; our contract draft was wrong, not the code
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("c65e59afc4e6086a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import sympy as sp

torch.manual_seed(0)

# The function uses:
# - func: a sympy expression string
# - N: number of samples (int)
# - range_min: minimum value for random range (float/int)
# - range_max: maximum value for random range (float/int)

ARGS = {
    "func": "x**2 + y + z",
    "N": 2,
    "range_min": -1.0,
    "range_max": 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sympy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
nrmse Ran
ran; our contract draft was wrong, not the code
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("046665644779835a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small sample tensors for y_true and y_pred
# Both should be 1D tensors with shape (num_samples,)
y_true = torch.randn(5)
y_pred = torch.randn(5)

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
SymboliRegression Not yet run
unverified (harvested, no recorded run)
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("4059642b29a80213")
How it ran

no invocation recorded.

SymbolicLayer Not yet run
unverified (harvested, no recorded run)
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("2a7001ad267d6941")
How it ran

no invocation recorded.

SymbolicNet Not yet run
unverified (harvested, no recorded run)
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("f21a4f8d0e19c1f7")
How it ran

no invocation recorded.

generate_data Not yet run
unverified (harvested, no recorded run)
ailwq/dysymnet/DySymNet/SymbolicRegression.py
code served (permissive licence) · get_code("8fc5b034a28064c8")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent deep generative SR methods have shown promising results. However, these methods face difficulties in processing high-dimensional problems and learning constants due to the large search space, and they don't scale well to unseen problems. In this work, we propose DYSYMNET, a novel neural-guided Dynamic Symbolic Network for SR. Instead of searching for expressions within a large search space, we explore symbolic networks with various structures, guided by reinforcement learning, and optimize them to identify expressions that better-fitting the data. Based on extensive numerical experiments on low-dimensional public standard benchmarks and the well-known SRBench with more variables, DYSYMNET shows clear superiority over several representative baseline models. Open source code is available at https: //github.com/AILWQ/DySymNet.

For agents

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

get_harvested_code_for_paper("2309.13705")
get_code_for_paper("2309.13705")
have("2309.13705")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2309.13705.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2309.13705.svg)](https://syntology.ai/paper/2309.13705)

Connect an agent — have() is free.