SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.10439 · 2018

Symbolic Execution for Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 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/1807.10439.json · badge: /api/ran/1807.10439.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
Koukyosyumei/Gymbo community (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
bf_to_gymbo Ran
ran on a synthesized input
Koukyosyumei/Gymbo/src/gymbo/brainfuck.py
code served (permissive licence) · get_code("bed38348da28907d")
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 str. 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.

# Construct arguments for bf_to_gymbo function

# The function takes a single parameter: bf (a Brainfuck program string)
# It processes the string character by character and converts it to a Gymbo assembly language

# Create a valid Brainfuck program string as input
# This is a simple Brainfuck program that increments a cell and outputs it
bf_program = "++++++++[>++++[>++>+++>+++>+<<<<-]>+>+>->>+[<]<-]>>.>---.+++++++..+++.>>.<-.<.+++.------.--------.>>+.>++."

ARGS = {
    "bf": bf_program
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
parse Ran
ran on a synthesized input
Koukyosyumei/Gymbo/src/gymbo/parser.py
code served (permissive licence) · get_code("939c9dd94329dc79")
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 Program. 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 torch.nn as nn

torch.manual_seed(0)

# The parse function takes a single parameter: source (a string)
# It parses assembly-like code with various directives and instructions

source = """
PARAM x = 0.5 @group1
PARAM y = 1.0 @group1
PARAM lr = 0.01

ENTRY start
DEPLOY end

start:
  LOAD $x
  ADD $y
  SQ
  ST [0]
  JZ skip
  MUL $lr
  OUT
  JMP end

skip:
  NOP

end:
  HALT
"""

ARGS = {
    'source': source
}
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 Program — a Program output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Program 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
parse_addr Ran
ran on a synthesized input
Koukyosyumei/Gymbo/src/gymbo/parser.py
code served (permissive licence) · get_code("c53445bb738abb96")
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 int, ndim 0, dtype family int, 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
import numpy as np

def parse_addr(tok):
    if tok.startswith('[') and tok.endswith(']'):
        return int(tok[1:-1])
    return int(tok)

ARGS = {
    'tok': '[42]'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
parse_operand Ran
ran on a synthesized input
Koukyosyumei/Gymbo/src/gymbo/parser.py
code served (permissive licence) · get_code("add945d39906ea73")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - tok: a string that can start with '$', '[', or be a number
# - params: a dictionary where keys are parameter names (strings)
#
# The function checks:
# 1. If tok starts with '$', it extracts name and looks it up in params dict
# 2. If tok starts with '[' and ends with ']', it parses the interior as int
# 3. Otherwise, it parses tok as float

# Create test cases for tok parameter
tok_param_ref = "$learning_rate"  # will test the '$' branch
tok_addr = "[42]"  # will test the '[...]' branch
tok_num = "3.14"  # will test the float branch

# Create params dictionary with a parameter that matches the '$' reference
params_dict = {
    "learning_rate": 0.001,
    "batch_size": 32,
    "hidden_dim": 128
}

# We'll test with the parameter reference case
ARGS = {
    "tok": tok_param_ref,
    "params": params_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
export Not yet run
unverified (harvested, no recorded run)
Koukyosyumei/Gymbo/src/gymbo/export.py
code served (permissive licence) · get_code("745a93abf29fa660")
How it ran

no invocation recorded.

run Not yet run
unverified (harvested, no recorded run)
Koukyosyumei/Gymbo/src/gymbo/vm.py
code served (permissive licence) · get_code("031bd2d96676f63a")
How it ran

no invocation recorded.

run_full Not yet run
unverified (harvested, no recorded run)
Koukyosyumei/Gymbo/src/gymbo/vm.py
code served (permissive licence) · get_code("669522cebd02747a")
How it ran

no invocation recorded.

run_hard Not yet run
unverified (harvested, no recorded run)
Koukyosyumei/Gymbo/src/gymbo/vm.py
code served (permissive licence) · get_code("8f1568feefb835f7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Deep Neural Networks (DNN) are increasingly used in a variety of applications, many of them with substantial safety and security concerns. This paper introduces DeepCheck, a new approach for validating DNNs based on core ideas from program analysis, specifically from symbolic execution. The idea is to translate a DNN into an imperative program, thereby enabling program analysis to assist with DNN validation. A basic translation however creates programs that are very complex to analyze. DeepCheck introduces novel techniques for lightweight symbolic analysis of DNNs and applies them in the context of image classification to address two challenging problems in DNN analysis: 1) identification of important pixels (for attribution and adversarial generation); and 2) creation of 1-pixel and 2-pixel attacks. Experimental results using the MNIST data-set show that DeepCheck's lightweight symbolic analysis provides a valuable tool for DNN validation.

For agents

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

get_harvested_code_for_paper("1807.10439")
get_code_for_paper("1807.10439")
have("1807.10439")

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

curl https://syntology.ai/api/ran/1807.10439.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.10439.svg)](https://syntology.ai/paper/1807.10439)

Connect an agent — have() is free.