SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.01969 · 2019

PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 1 failure of our instrument; 2 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/1903.01969.json · badge: /api/ran/1903.01969.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
Microsoft/PDP-Solver canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
negotiatorvivian/PDP-SP community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
is_sat Ran
ran on a synthesized input
Microsoft/PDP-Solver/src/pdp/generator.py
code served (permissive licence) · get_code("79e12ce4b848bc39")
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 bool, 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
import numpy as np

torch.manual_seed(0)

# The function signature is: is_sat(_var_num, iclause_list)
# Based on the function body, it takes:
# - _var_num: an integer representing the number of variables
# - iclause_list: a list of clauses (likely for SAT solving)

# Create minimal valid arguments
_var_num = 5
iclause_list = [
    [1, 2, -3],
    [-1, 3, 4],
    [2, -4, 5],
    [-2, -3, -5]
]

ARGS = {
    "_var_num": _var_num,
    "iclause_list": iclause_list
}
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 bool, 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
safe_exp Ran
ran on a synthesized input
Microsoft/PDP-Solver/src/pdp/nn/util.py
code served (permissive licence) · get_code("449159ff0937d675")
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 for x parameter
x = torch.randn(2, 4)

# Create a device (CPU only)
device = torch.device('cpu')

ARGS = {
    'x': x,
    'device': device
}
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
sequence_mask Ran
ran; our contract draft was wrong, not the code
negotiatorvivian/PDP-SP/src/pdp/nn/attention.py
pointer only (licence: MIT) · get_code("a4e81f0f0be4c23d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, negotiatorvivian/PDP-SP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sparse_argmax Ran
ran on a synthesized input
Microsoft/PDP-Solver/src/pdp/nn/util.py
code served (permissive licence) · get_code("f695327ff91160dc")
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 int, shape (3,) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 sparse tensor mask
# The function expects mask to have _indices() and size() methods
# This is typical of torch.sparse tensors
indices = torch.tensor([[0, 1, 2], [0, 1, 2]], dtype=torch.long)
values = torch.ones(3)
mask = torch.sparse_coo_tensor(indices, values, (3, 3), dtype=torch.float32)

# Create a dense vector x that matches the sparsity pattern
# x should have the same number of elements as the non-zero entries in mask
x = torch.tensor([1.5, 2.3, 0.8], dtype=torch.float32)

# Device - CPU only
device = torch.device('cpu')

ARGS = {
    'x': x,
    'mask': mask,
    'device': device
}
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 1, dtype family int, shape (3,) — shape (3,) 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
sparse_max Ran
ran on a synthesized input
Microsoft/PDP-Solver/src/pdp/nn/util.py
code served (permissive licence) · get_code("638459184cc132fd")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 sparse mask
# sparse_max expects mask._indices() and mask.size()
# We'll create a sparse tensor with shape (2, 4)
indices = torch.tensor([[0, 1], [0, 2]], dtype=torch.long)
values = torch.ones(2)
mask = torch.sparse_coo_tensor(indices, values, (2, 4))

# Create a dense input vector x
# x should be a 1D tensor with same length as number of non-zero elements in mask
x = torch.tensor([1.5, 2.3], dtype=torch.float32)

# Device set to CPU
device = torch.device('cpu')

ARGS = {
    'x': x,
    'mask': mask,
    'device': device
}
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 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
mask Not yet run
unverified (harvested, no recorded run)
negotiatorvivian/PDP-SP/src/pdp/nn/attention.py
pointer only (licence: MIT) · get_code("67b02f95734304ef")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, negotiatorvivian/PDP-SP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

position_embedding Not yet run
unverified (harvested, no recorded run)
negotiatorvivian/PDP-SP/src/pdp/nn/attention.py
pointer only (licence: MIT) · get_code("ff31b01f9c2b4b49")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, negotiatorvivian/PDP-SP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

FunctionAlso present inEarliest-datedOthers named
sequence_mask 1 other paper
1 dated earlier
1811.07234 (2018-11)
Improving Automatic Source Code Summarization via Deep Reinforcement Learning

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

There have been recent efforts for incorporating Graph Neural Network models for learning full-stack solvers for constraint satisfaction problems (CSP) and particularly Boolean satisfiability (SAT). Despite the unique representational power of these neural embedding models, it is not clear how the search strategy in the learned models actually works. On the other hand, by fixing the search strategy (e.g. greedy search), we would effectively deprive the neural models of learning better strategies than those given. In this paper, we propose a generic neural framework for learning CSP solvers that can be described in terms of probabilistic inference and yet learn search strategies beyond greedy search. Our framework is based on the idea of propagation, decimation and prediction (and hence the name PDP) in graphical models, and can be trained directly toward solving CSP in a fully unsupervised manner via energy minimization, as shown in the paper. Our experimental results demonstrate the effectiveness of our framework for SAT solving compared to both neural and the state-of-the-art baselines.

For agents

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

get_harvested_code_for_paper("1903.01969")
get_code_for_paper("1903.01969")
have("1903.01969")

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

curl https://syntology.ai/api/ran/1903.01969.json

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

[![Syntology run record](https://syntology.ai/api/ran/1903.01969.svg)](https://syntology.ai/paper/1903.01969)

Connect an agent — have() is free.