SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.08397 · 2023

Scalable Neural-Probabilistic Answer Set Programming

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 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/2306.08397.json · badge: /api/ran/2306.08397.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
ml-research/slash canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_models_splitwise Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ml-research/slash/src/SLASH/slash.py
code served (permissive licence) · get_code("6ca29a8fe9e2ebf9")
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 numpy as np

torch.manual_seed(0)

class MockDMVPP:
    """Mock class for the dmvpp object based on how it's used in compute_models_splitwise"""
    def __init__(self):
        self.M = None
    
    def normalize_M(self):
        """Mock normalize method"""
        if self.M is not None:
            self.M = self.M / (self.M.sum() + 1e-8)
    
    def find_all_SM_under_query(self, query):
        """Return mock models"""
        return [{"atom1": 0.5, "atom2": 0.3}]
    
    def find_k_most_probable_SM_under_query_noWC(self, query, k=1):
        """Return mock models"""
        return [{"atom1": 0.5}] * min(k, 2)
    
    def find_SM_vqa_with_same(self, query, k=1, threshold=0.5, obj_filter=None, vqa_params=None):
        """Return mock models"""
        return [{"atom1": 0.5}]
    
    def find_SM_with_same(self, query, k=1, threshold=0.5):
        """Return mock models"""
        return [{"atom1": 0.5}]
    
    def find_k_most_probable_SM_with_same(self, query, k=1):
        """Return mock models"""
        return [{"atom1": 0.5}]
    
    def collect_atom_idx(self, models):
        """Return mock atom indices"""
        return [0, 1, 2]

# Create mock objects
big_M_split = torch.randn(3, 2, 4)  # Shape: (num_atoms, batch_size, dims)
query_batch_split = np.array([
    "digit(0, +i1, -0)",
    "digit(1, +i2, -1)"
])
dmvpp = MockDMVPP()
method = "exact"
k = 5
same_threshold = 0.5
obj_filter = None
vqa_params = {"param1": 0.1, "param2": 0.2}

ARGS = {
    "big_M_split": big_M_split,
    "query_batch_split": query_batch_split,
    "dmvpp": dmvpp,
    "method": method,
    "k": k,
    "same_threshold": same_threshold,
    "obj_filter": obj_filter,
    "vqa_params": vqa_params
}
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 — 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
pad_3d_tensor Ran
ran, honoured the contract we drafted
ml-research/slash/src/SLASH/slash.py
code served (permissive licence) · get_code("20f02868fe077f82")
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 3, dtype family float, shape (2, 3, 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
import numpy as np

torch.manual_seed(0)

# Construct a 3D nested list structure
# bs=2 (batch size), ruleNum=3 (max rules), max_classes=4 (max classes)
# Each batch contains rows of varying lengths up to max_classes
target = [
    [
        [0.1, 0.2],
        [0.3, 0.4, 0.5],
        [0.6]
    ],
    [
        [0.7, 0.8, 0.9],
        [0.2],
        [0.3, 0.4]
    ]
]

framework = 'numpy'
bs = 2
ruleNum = 3
max_classes = 4

ARGS = {
    'target': target,
    'framework': framework,
    'bs': bs,
    'ruleNum': ruleNum,
    'max_classes': max_classes
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
replace_plus_minus_occurences Ran
ran; our contract draft was wrong, not the code
ml-research/slash/src/SLASH/slash.py
code served (permissive licence) · get_code("6edc35fb0e836819")
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 re

# The function takes a single parameter: pi_prime, which is a string containing
# a query/program with +- notation that needs to be converted to ASP readable format.
# The function uses regex patterns to find and replace various combinations of +/- operators.

# Create a sample input string with various +- notation patterns
pi_prime = """
digit(0, +i1, -0).
digit(1, -X, +Y).
relation(A, +(B,C), -D).
test(E, +F, +G).
other(H, -I, -J).
"""

ARGS = {
    "pi_prime": pi_prime
}
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 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI. Deep Probabilistic Programming Languages (DPPLs) have been developed for probabilistic logic programming to be carried out via the probability estimations of deep neural networks. However, recent SOTA DPPL approaches allow only for limited conditional probabilistic queries and do not offer the power of true joint probability estimation. In our work, we propose an easy integration of tractable probabilistic inference within a DPPL. To this end, we introduce SLASH, a novel DPPL that consists of Neural-Probabilistic Predicates (NPPs) and a logic program, united via answer set programming (ASP). NPPs are a novel design principle allowing for combining all deep model types and combinations thereof to be represented as a single probabilistic predicate. In this context, we introduce a novel $+/-$ notation for answering various types of probabilistic queries by adjusting the atom notations of a predicate. To scale well, we show how to prune the stochastically insignificant parts of the (ground) program, speeding up reasoning without sacrificing the predictive performance. We evaluate SLASH on a variety of different tasks, including the benchmark task of MNIST addition and Visual Question Answering (VQA).

For agents

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

get_harvested_code_for_paper("2306.08397")
get_code_for_paper("2306.08397")
have("2306.08397")

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

curl https://syntology.ai/api/ran/2306.08397.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.08397.svg)](https://syntology.ai/paper/2306.08397)

Connect an agent — have() is free.