SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.12854 · 2020

Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 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/2011.12854.json · badge: /api/ran/2011.12854.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/NeSyXIL canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
run_test_final Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ml-research/NeSyXIL/src/clevr_hans/cnn/train_resnet34_xil.py
code served (permissive licence) · get_code("902801a457ed91db")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple. 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.utils.data import Dataset, DataLoader
import numpy as np

torch.manual_seed(0)

# Simple network that outputs class logits
class SimpleNet(nn.Module):
    def __init__(self, num_classes=3):
        super().__init__()
        self.fc = nn.Linear(12, num_classes)  # 12 = 3*2*2 flattened
    
    def forward(self, x):
        # x shape: (batch, 3, 2, 2)
        x = x.view(x.size(0), -1)
        return self.fc(x)

# Simple dataset
class SimpleDataset(Dataset):
    def __init__(self, num_samples=4):
        self.num_samples = num_samples
        
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        imgs = torch.randn(3, 2, 2)  # C, H, W
        target_set = torch.randn(5)  # some target set
        img_class_ids = torch.tensor(idx % 3)  # class id (0, 1, or 2)
        img_ids = torch.tensor(idx)
        dummy1 = torch.tensor(0.0)
        dummy2 = torch.tensor(0.0)
        return imgs, target_set, img_class_ids, img_ids, dummy1, dummy2

# Create network
net = SimpleNet(num_classes=3)

# Create data loader
dataset = SimpleDataset(num_samples=4)
loader = DataLoader(dataset, batch_size=2, shuffle=False)

# Create criterion
criterion = nn.CrossEntropyLoss()

# Create a simple writer stand-in
class SimpleWriter:
    def add_scalar(self, tag, value, step):
        pass

writer = SimpleWriter()

# Create args stand-in
class Args:
    pass

args = Args()

datasplit = "test"

ARGS = {
    "net": net,
    "loader": loader,
    "criterion": criterion,
    "writer": writer,
    "args": args,
    "datasplit": datasplit
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, sklearn, torch, tqdm — 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
run_test_final Not yet run
unverified (harvested, no recorded run)
ml-research/NeSyXIL/src/clevr_hans/nesy_xil/train_clevr_hans_concept_learner_xil.py
code served (permissive licence) · get_code("13614f949779b0bc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover, without insights into the model's semantic concept, it is difficult -- if not impossible -- to intervene on the model's behavior via its explanations, called Explanatory Interactive Learning. Consequently, we propose to intervene on a Neuro-Symbolic scene representation, which allows one to revise the model on the semantic level, e.g. "never focus on the color to make your decision". We compiled a novel confounded visual scene data set, the CLEVR-Hans data set, capturing complex compositions of different objects. The results of our experiments on CLEVR-Hans demonstrate that our semantic explanations, i.e. compositional explanations at a per-object level, can identify confounders that are not identifiable using "visual" explanations only. More importantly, feedback on this semantic level makes it possible to revise the model from focusing on these factors.

For agents

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

get_harvested_code_for_paper("2011.12854")
get_code_for_paper("2011.12854")
have("2011.12854")

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

curl https://syntology.ai/api/ran/2011.12854.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.12854.svg)](https://syntology.ai/paper/2011.12854)

Connect an agent — have() is free.