SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.07243 · 2018

Learning Conditioned Graph Structures for Interpretable Visual Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures 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/1806.07243.json · badge: /api/ran/1806.07243.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
aimbrain/vqa-project canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_to_cuda Ran
ran on a synthesized input
aimbrain/vqa-project/utils.py
code served (permissive licence) · get_code("736573dfab51b4df")
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. 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
from torch.autograd import Variable

torch.manual_seed(0)

# The function expects batch to be a tuple/list with at least 7 elements
# batch[0] = q (tensor)
# batch[1] = a (tensor)
# batch[2] = n_votes (tensor)
# batch[4] = i (tensor)
# batch[5] = k (tensor)
# batch[6] = qlen (list or tensor that can be converted to list)

q_tensor = torch.randn(2, 4)
a_tensor = torch.randn(2, 3)
n_votes_tensor = torch.randn(2, 5)
placeholder_tensor = torch.randn(2, 6)  # batch[3] - not used but needed for indexing
i_tensor = torch.randn(2, 7)
k_tensor = torch.randn(2, 8)
qlen_tensor = torch.tensor([4, 3])

batch = (
    q_tensor,
    a_tensor,
    n_votes_tensor,
    placeholder_tensor,
    i_tensor,
    k_tensor,
    qlen_tensor
)

ARGS = {
    "batch": batch,
    "volatile": False
}
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
collate_fn Ran
ran on a synthesized input
aimbrain/vqa-project/torch_dataset.py
code served (permissive licence) · get_code("88f937451ae9b61b")
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. 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 dataloader

torch.manual_seed(0)

# Create a batch of tuples containing (features, labels)
# Each item is a tuple where the last element is a sortable value (the label)
batch = [
    (torch.randn(4), torch.tensor(3)),
    (torch.randn(4), torch.tensor(1)),
    (torch.randn(4), torch.tensor(5)),
    (torch.randn(4), torch.tensor(2)),
]

ARGS = {
    "batch": batch
}
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 list — a list 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
total_vqa_score Not yet run
unverified (harvested, no recorded run)
aimbrain/vqa-project/utils.py
code served (permissive licence) · get_code("0436718db3a26f78")
How it ran

no invocation recorded.

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

Visual Question answering is a challenging problem requiring a combination of concepts from Computer Vision and Natural Language Processing. Most existing approaches use a two streams strategy, computing image and question features that are consequently merged using a variety of techniques. Nonetheless, very few rely on higher level image representations, which can capture semantic and spatial relationships. In this paper, we propose a novel graph-based approach for Visual Question Answering. Our method combines a graph learner module, which learns a question specific graph representation of the input image, with the recent concept of graph convolutions, aiming to learn image representations that capture question specific interactions. We test our approach on the VQA v2 dataset using a simple baseline architecture enhanced by the proposed graph learner module. We obtain promising results with 66.18% accuracy and demonstrate the interpretability of the proposed method. Code can be found at github.com/aimbrain/vqa-project.

For agents

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

get_harvested_code_for_paper("1806.07243")
get_code_for_paper("1806.07243")
have("1806.07243")

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

curl https://syntology.ai/api/ran/1806.07243.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.07243.svg)](https://syntology.ai/paper/1806.07243)

Connect an agent — have() is free.