SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.01242 · ICML · 2023

Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal

Simone Calderara, Stefano Teso, Andrea Passerini, Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure 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/2302.01242.json · badge: /api/ran/2302.01242.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
ema-marconato/nesy-cl canonical (classifier label)
classifier basis: classifier_2025
3 ran · 4 no recorded run
FunctionStatusWhere it lives
Buffer Ran
ran on a synthesized input · constructed an object; no result was computed
ema-marconato/nesy-cl/models/cool.py
code served (permissive licence) · get_code("d9319734afd720b0")
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 an instance of its own class, Buffer: the run constructed the object and did not call it, so no result was computed. 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
from torchvision import transforms

torch.manual_seed(0)
np.random.seed(0)

ARGS = {
    'buffer_size': 10,
    'device': torch.device('cpu'),
    'n_tasks': None,
    'mode': 'reservoir'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Buffer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Buffer 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
ContinualModel Ran
ran on a synthesized input · constructed an object; no result was computed
ema-marconato/nesy-cl/models/cool.py
code served (permissive licence) · get_code("68ac932d64459c47")
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 an instance of its own class, ContinualModel: the run constructed the object and did not call it, so no result was computed. 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 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
from torch.optim import Adam
import torchvision
from argparse import Namespace
import torchvision.transforms as transforms

torch.manual_seed(0)

# Define a minimal backbone network
class SimpleBackbone(nn.Module):
    def __init__(self):
        super(SimpleBackbone, self).__init__()
        self.fc = nn.Linear(4, 10)
    
    def forward(self, x):
        return self.fc(x)

# Define a minimal loss function
class SimpleLoss(nn.Module):
    def __init__(self):
        super(SimpleLoss, self).__init__()
        self.ce = nn.CrossEntropyLoss()
    
    def forward(self, x, y):
        return self.ce(x, y)

# Define a minimal transform
transform = transforms.Compose([
    transforms.ToTensor(),
])

# Create the arguments dictionary
ARGS = {
    'backbone': SimpleBackbone(),
    'loss': SimpleLoss(),
    'args': Namespace(
        lr=0.001,
        batch_size=2,
        epochs=1
    ),
    'transform': transform
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ContinualModel — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ContinualModel 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
kl_divergence Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ema-marconato/nesy-cl/models/cool.py
code served (permissive licence) · get_code("79ad7949ae4becd4")
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 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
torch.manual_seed(0)

# For dim=2, input and target need to be splittable into chunks of 10 along dim=1
# So we need at least 10 elements in dim=1 (or 20 for multiple chunks)
# Let's use batch_size=2, and 20 features to get 2 chunks of 10
input_2d = torch.rand(2, 20)
target_2d = torch.rand(2, 20)

# For dim=1, input and target are 1D tensors
input_1d = torch.rand(10)
target_1d = torch.rand(10)

ARGS = {
    'input': input_2d,
    'target': target_2d,
    'dim': 2,
    'version': 'nesy'
}
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 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
COOL Not yet run
unverified (harvested, no recorded run)
ema-marconato/nesy-cl/models/cool.py
code served (permissive licence) · get_code("b2e185f86bccea7a")
How it ran

no invocation recorded.

launch_addition_mnist Not yet run
unverified (harvested, no recorded run)
ema-marconato/nesy-cl/experiments.py
code served (permissive licence) · get_code("17f4941b9c6da030")
How it ran

no invocation recorded.

launch_cle4evr Not yet run
unverified (harvested, no recorded run)
ema-marconato/nesy-cl/experiments.py
code served (permissive licence) · get_code("0ebffe9e2281cd63")
How it ran

no invocation recorded.

launch_shortcut_mnist Not yet run
unverified (harvested, no recorded run)
ema-marconato/nesy-cl/experiments.py
code served (permissive licence) · get_code("643a5c5e5c5368f6")
How it ran

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, 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 7 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 introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map subsymbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior knowledge. Our key observation is that neuro-symbolic tasks, although different, often share concepts whose semantics remains stable over time. Traditional approaches fall short: existing continual strategies ignore knowledge altogether, while stock neuro-symbolic architectures suffer from catastrophic forgetting. We show that leveraging prior knowledge by combining neurosymbolic architectures with continual strategies does help avoid catastrophic forgetting, but also that doing so can yield models affected by reasoning shortcuts. These undermine the semantics of the acquired concepts, even when detailed prior knowledge is provided upfront and inference is exact, and in turn continual performance. To overcome these issues, we introduce COOL, a COncept-level cOntinual Learning strategy tailored for neuro-symbolic continual problems that acquires high-quality concepts and remembers them over time. Our experiments on three novel benchmarks highlights how COOL attains sustained high performance on neuro-symbolic continual learning tasks in which other strategies fail. 1

For agents

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

get_harvested_code_for_paper("2302.01242")
get_code_for_paper("2302.01242")
have("2302.01242")

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

curl https://syntology.ai/api/ran/2302.01242.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.01242.svg)](https://syntology.ai/paper/2302.01242)

Connect an agent — have() is free.