SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.01464 · NeurIPS · 2020

Visual Concept-Metaconcept Learning

Chi Han, Jiayuan Mao, Chuang Gan, Joshua Tenenbaum, Jiajun Wu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 4 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2002.01464.json · badge: /api/ran/2002.01464.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
Glaciohound/VCML canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
concatenate_origin Ran
ran on a synthesized input
Glaciohound/VCML/models/visualize/visualize_utils.py
code served (permissive licence) · get_code("c93ee3320d43644b")
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 numpy as np

# Create sample data for the function
names = ['embedding_1', 'embedding_2', 'embedding_3']
embeddings = np.random.randn(3, 4)  # 3 embeddings of dimension 4

ARGS = {
    'names': names,
    'embeddings': embeddings
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
get_dataloader Ran
ran on a synthesized input
Glaciohound/VCML/dataset/dataloader.py
code served (permissive licence) · get_code("0950c506f8029e50")
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 DataLoader. 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
from torch.utils.data import Dataset

torch.manual_seed(0)

class DummyDataset(Dataset):
    def __init__(self, size=8, input_dim=4, output_dim=3):
        self.size = size
        self.input_dim = input_dim
        self.output_dim = output_dim
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        x = torch.randn(self.input_dim)
        y = torch.randint(0, self.output_dim, (1,)).item()
        return (x, y)

def dummy_collate_fn(batch):
    xs = torch.stack([item[0] for item in batch])
    ys = torch.tensor([item[1] for item in batch])
    return (xs, ys)

class Args:
    def __init__(self):
        self.num_workers = 0
        self.batch_size = 2
        self.shuffle = True

dataset = DummyDataset(size=8, input_dim=4, output_dim=3)
collate_fn = dummy_collate_fn
args = Args()

ARGS = {
    'dataset': dataset,
    'collate_fn': collate_fn,
    'args': args
}
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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
get_embedding_dict Ran
ran on a synthesized input
Glaciohound/VCML/models/visualize/visualize_sets_v2.py
code served (permissive licence) · get_code("e3d3fe253a528449")
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 torch.nn as nn

torch.manual_seed(0)

class MockEmbedding(nn.Module):
    def __init__(self):
        super().__init__()
        self.tools = MockTools()
        self._embeddings = torch.randn(5, 4)
    
    def all_concept_embeddings(self):
        return self._embeddings

class MockTools:
    def __init__(self):
        self.concepts = ["concept_0", "concept_1", "concept_2", "concept_3", "concept_4"]

embedding = MockEmbedding()

ARGS = {
    "embedding": embedding
}
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 — 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
get_filename Ran
ran on a synthesized input
Glaciohound/VCML/models/visualize/temp.py
code served (permissive licence) · get_code("92eafa31e92c7dda")
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 str. 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 os
import tempfile

# Create a temporary directory for the path
temp_dir = tempfile.gettempdir()

ARGS = {
    'name': 'test_image',
    'sub_folder': 'images',
    'path': temp_dir
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Humans reason with concepts and metaconcepts: we recognize red and green from visual input; we also understand that they describe the same property of objects (i.e., the color). In this paper, we propose the visual concept-metaconcept learner (VCML) for joint learning of concepts and metaconcepts from images and associated question-answer pairs. The key is to exploit the bidirectional connection between visual concepts and metaconcepts. Visual representations provide grounding cues for predicting relations between unseen pairs of concepts. Knowing that red and green describe the same property of objects, we generalize to the fact that cube and sphere also describe the same property of objects, since they both categorize the shape of objects. Meanwhile, knowledge about metaconcepts empowers visual concept learning from limited, noisy, and even biased data. From just a few examples of purple cubes we can understand a new color purple, which resembles the hue of the cubes instead of the shape of them. Evaluation on both synthetic and real-world datasets validates our claims.

For agents

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

get_harvested_code_for_paper("2002.01464")
get_code_for_paper("2002.01464")
have("2002.01464")

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

curl https://syntology.ai/api/ran/2002.01464.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.01464.svg)](https://syntology.ai/paper/2002.01464)

Connect an agent — have() is free.