SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.23810 · 2026

REASONX: Declarative Reasoning on Explanations

Salvatore Ruggieri, Laura State, Franco Turini, Alexander Von

arXiv · PDF

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; 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/2602.23810.json · badge: /api/ran/2602.23810.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
lstate/reasonx canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
argmax Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lstate/reasonx/src/dautils.py
code served (permissive licence) · get_code("ce70e689f61c1793")
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

torch.manual_seed(0)

# The argmax function takes an iterable of values and finds the index and max value
# It uses enumerate() and max() with a lambda function
# The values parameter should be an iterable (list, tuple, tensor, etc.)

values = [3.2, 1.5, 7.8, 2.1]

ARGS = {
    "values": values
}
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 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
flatten Ran
ran, honoured the contract we drafted
lstate/reasonx/src/dautils.py
code served (permissive licence) · get_code("75710c63acdaa0b0")
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 list, ndim 1, dtype family int; 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)

# The flatten function takes a single parameter 'l' which should be a nested list structure
# The function recursively flattens lists of any depth
# Test with a deeply nested list structure

nested_list = [
    [[1, 2], [3, 4]],
    [5, [6, 7]],
    8,
    [[9], 10]
]

ARGS = {
    "l": nested_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 list, ndim 1, dtype family int — a list 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
getReader Ran
ran; our contract draft was wrong, not the code
lstate/reasonx/src/dautils.py
code served (permissive licence) · get_code("83daf3a54822c211")
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 TextIOWrapper. 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 sys
import urllib
import gzip
import codecs
import tempfile
import os

# Create a temporary test file for testing
temp_dir = tempfile.gettempdir()
test_file = os.path.join(temp_dir, "test_reader.txt")
with open(test_file, 'w', encoding='utf8') as f:
    f.write("test content\n")

# Create a temporary gzipped test file
test_gz_file = os.path.join(temp_dir, "test_reader.txt.gz")
with gzip.open(test_gz_file, 'wt', encoding='utf8') as f:
    f.write("gzipped test content\n")

ARGS = {
    'filename': test_file,
    'encoding': 'utf8'
}
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 TextIOWrapper — a TextIOWrapper 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

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

Explaining opaque Machine Learning (ML) models has become an increasingly important challenge. However, current eXplanation in AI (XAI) methods suffer several shortcomings, including insufficient abstraction, limited user interactivity, and inadequate integration of symbolic knowledge. We propose REASONX, an explanation tool based on expressions (or, queries) in a closed algebra of operators over theories of linear constraints. REASONX provides declarative and interactive explanations for decision trees, which may represent the ML models under analysis or serve as global or local surrogate models for any black-box predictor. Users can express background or common sense knowledge as linear constraints. This allows for reasoning at multiple levels of abstraction, ranging from fully specified examples to under-specified or partially constrained ones. REASONX leverages Mixed-Integer Linear Programming (MILP) to reason over the features of factual and contrastive instances. We present here the architecture of REASONX, which consists of a Python layer, closer to the user, and a Constraint Logic Programming (CLP) layer, which implements a meta-interpreter of the query algebra. The capabilities of REASONX are demonstrated through qualitative examples, and compared to other XAI tools through quantitative experiments.

For agents

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

get_harvested_code_for_paper("2602.23810")
get_code_for_paper("2602.23810")
have("2602.23810")

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

curl https://syntology.ai/api/ran/2602.23810.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.23810.svg)](https://syntology.ai/paper/2602.23810)

Connect an agent — have() is free.