SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.09949 · 2024

Neural Concept Binder

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 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/2406.09949.json · badge: /api/ran/2406.09949.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/neuralconceptbinder canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
gather_encs Ran
ran, honoured the contract we drafted
ml-research/neuralconceptbinder/inference_example.py
code served (permissive licence) · get_code("697614f37e445348")
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 ndarray, ndim 2, dtype family float, shape (4, 7) 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 torch.nn as nn
import numpy as np

torch.manual_seed(0)

class StandInModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.dummy = nn.Linear(3, 5)
    
    def encode(self, imgs):
        batch_size = imgs.shape[0]
        codes = torch.randn(batch_size, 7)
        probs = torch.randn(batch_size, 9)
        return codes, probs
    
    def eval(self):
        pass

class StandInArgs:
    def __init__(self):
        self.device = 'cpu'
        self.batch_size = 2

model = StandInModel()

# Create a loader with samples
# Each sample is a tuple: (imgs, label1, label2, label3, img_locs)
# The function unpacks sample[-1] as img_locs and sample[:-1] as the rest
# Then it unpacks 4 items from sample[:-1]: imgs, _, _, _
sample1 = (
    torch.randn(2, 3, 8, 8),  # imgs
    torch.randn(2, 4),         # placeholder 1
    torch.randn(2, 5),         # placeholder 2
    torch.randn(2, 6),         # placeholder 3
    ['img1.jpg', 'img2.jpg']   # img_locs
)

sample2 = (
    torch.randn(2, 3, 8, 8),  # imgs
    torch.randn(2, 4),         # placeholder 1
    torch.randn(2, 5),         # placeholder 2
    torch.randn(2, 6),         # placeholder 3
    ['img3.jpg', 'img4.jpg']   # img_locs
)

loader = [sample1, sample2]

args = StandInArgs()

ARGS = {
    'model': model,
    'loader': loader,
    'args': args
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 7) — shape (4, 7) 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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 challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct. Achieving this in an unsupervised manner requires human users to understand the model's learned concepts and, if necessary, revise incorrect ones. To address this challenge, we introduce the Neural Concept Binder (NCB), a novel framework for deriving both discrete and continuous concept representations, which we refer to as "concept-slot encodings". NCB employs two types of binding: "soft binding", which leverages the recent SysBinder mechanism to obtain object-factor encodings, and subsequent "hard binding", achieved through hierarchical clustering and retrieval-based inference. This enables obtaining expressive, discrete representations from unlabeled images. Moreover, the structured nature of NCB's concept representations allows for intuitive inspection and the straightforward integration of external knowledge, such as human input or insights from other AI models like GPT-4. Additionally, we demonstrate that incorporating the hard binding mechanism preserves model performance while enabling seamless integration into both neural and symbolic modules for complex reasoning tasks. We validate the effectiveness of NCB through evaluations on our newly introduced CLEVR-Sudoku dataset.

For agents

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

get_harvested_code_for_paper("2406.09949")
get_code_for_paper("2406.09949")
have("2406.09949")

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

curl https://syntology.ai/api/ran/2406.09949.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.09949.svg)](https://syntology.ai/paper/2406.09949)

Connect an agent — have() is free.