SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.13155 · NeurIPS · 2020

Logical Neural Networks

Ryan Riegel, Alexander Gray, Francois Luus, Naweed Khan, Ndivhuwo Makondo, Ismail Yunus Akhalwaya, Haifeng Qian, Ronald Fagin, Francisco Barahona, Udit Sharma, Hima Karanam, Sumit Neelam, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

2 of 15 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, 2 violated it and 0 have no contract verdict; 0 failures of our instrument; 13 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/2006.13155.json · badge: /api/ran/2006.13155.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
IBM/LNN marked official in Papers with Code
Papers with Code archive
2 ran · 12 no recorded run
ibm/torchlogic community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
tensorise Ran
ran, violated the contract we drafted
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("9469f676588b9dae")
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 Tensor, ndim 1, dtype family float, shape (4,) 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

torch.manual_seed(0)

# Test case 1: torch.Tensor input
tensor_input = torch.tensor([1.0, 2.0, 3.0, 4.0])

# Test case 2: np.ndarray input
ndarray_input = np.array([True, False, True, False])

# Test case 3: np.bool_ input (NumPy 2.0)
bool_scalar_input = np.bool_(True)

# Test case 4: Python bool input
python_bool_input = True

ARGS = {
    "t": tensor_input
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
val_clamp Ran
ran, violated the contract we drafted
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("8620647772af6e0d")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 a small tensor with values that will test the clamping behavior
x = torch.tensor([[-0.5, 0.3, 0.7, 1.2], [0.1, 0.5, 0.9, 1.5]], dtype=torch.float32, requires_grad=True)

ARGS = {
    "x": x,
    "_min": 0.0,
    "_max": 1.0,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
Bound Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("a414e494c28e8b53")
How it ran

no invocation recorded.

Direction Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("9cd1417770609993")
How it ran

no invocation recorded.

Fact Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("ccc83f56566983c4")
How it ran

no invocation recorded.

LukasiewiczCore Not yet run
unverified (harvested, no recorded run)
ibm/torchlogic/torchlogic/nn/base/_core.py
code served (permissive licence) · get_code("550a53b2c8bb092f")
How it ran

no invocation recorded.

World Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("e2478de9c6a50e03")
How it ran

no invocation recorded.

_AutoName Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("53fb477a4312f8da")
How it ran

no invocation recorded.

_NeuronActivation Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("556cd4e7b9148784")
How it ran

no invocation recorded.

_NeuronParameters Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("32d9abf50ba946c7")
How it ran

no invocation recorded.

_NodeActivation Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("73b4875866816be7")
How it ran

no invocation recorded.

_NodeParameters Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("d5b3cf2c88214d88")
How it ran

no invocation recorded.

bool_and Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("5481e5e04cffed09")
How it ran

no invocation recorded.

bool_or Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("266c294a99762150")
How it ran

no invocation recorded.

bool_tensor Not yet run
unverified (harvested, no recorded run)
IBM/LNN/lnn/neural/activations/neuron/neuron.py
code served (permissive licence) · get_code("8136d8c3c05c97ff")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 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 15 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

We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning). Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omnidirectional rather than focused on predefined target variables, and corresponds to logical reasoning, including classical first-order logic theorem proving as a special case. The model is end-to-end differentiable, and learning minimizes a novel loss function capturing logical contradiction, yielding resilience to inconsistent knowledge. It also enables the open-world assumption by maintaining bounds on truth values which can have probabilistic semantics, yielding resilience to incomplete knowledge. Preprint. Under review.

For agents

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

get_harvested_code_for_paper("2006.13155")
get_code_for_paper("2006.13155")
have("2006.13155")

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

curl https://syntology.ai/api/ran/2006.13155.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.13155.svg)](https://syntology.ai/paper/2006.13155)

Connect an agent — have() is free.