SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.01855 · 2018

Explainable and Explicit Visual Reasoning over Scene Graphs

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 0 have no contract verdict; 2 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/1812.01855.json · badge: /api/ran/1812.01855.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
shijx12/XNM-Net canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
invert_dict Ran
ran; our contract draft was wrong, not the code
shijx12/XNM-Net/utils/misc.py
code served (permissive licence) · get_code("e6dbe2d3b6f0cc87")
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 dict. 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

torch.manual_seed(0)

# invert_dict takes a dictionary and inverts its key-value pairs
# It simply iterates over d.items() and creates a new dict with swapped k,v
# No special attributes or methods are required - just a standard dict

d = {
    "key1": "value1",
    "key2": "value2",
    "key3": "value3"
}

ARGS = {
    "d": d
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
todevice Ran
ran; our contract draft was wrong, not the code
shijx12/XNM-Net/utils/misc.py
code served (permissive licence) · get_code("6d12da501ae235a1")
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

torch.manual_seed(0)

# Test case 1: Single tensor
tensor_single = torch.randn(2, 4)
device_cpu = 'cpu'

# Test case 2: List of tensors
tensor_list = [torch.randn(2, 4), torch.randn(3, 5)]

# Test case 3: Tuple of tensors
tensor_tuple = (torch.randn(2, 4), torch.randn(3, 5))

# The function can handle either a single tensor or a list/tuple of tensors
# We'll test with a list case
ARGS = {
    'tensor': tensor_list,
    'device': device_cpu
}
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
convert_david_program_to_mine Not yet run
unverified (harvested, no recorded run)
shijx12/XNM-Net/utils/misc.py
code served (permissive licence) · get_code("df94cf849791c151")
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, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
invert_dict 6 other papers
1 dated earlier, 5 later
1803.05268 (2018-03)
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
2211.03779 (2022-11)
CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering
2212.14454 (2022-12)
MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid
and 3 more not named here
todevice 1 other paper
1 later
2211.03779 (2022-11)
CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering

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 aim to dismantle the prevalent black-box neural architectures used in complex visual reasoning tasks, into the proposed eXplainable and eXplicit Neural Modules (XNMs), which advance beyond existing neural module networks towards using scene graphs --- objects as nodes and the pairwise relationships as edges --- for explainable and explicit reasoning with structured knowledge. XNMs allow us to pay more attention to teach machines how to "think", regardless of what they "look". As we will show in the paper, by using scene graphs as an inductive bias, 1) we can design XNMs in a concise and flexible fashion, i.e., XNMs merely consist of 4 meta-types, which significantly reduce the number of parameters by 10 to 100 times, and 2) we can explicitly trace the reasoning-flow in terms of graph attentions. XNMs are so generic that they support a wide range of scene graph implementations with various qualities. For example, when the graphs are detected perfectly, XNMs achieve 100% accuracy on both CLEVR and CLEVR CoGenT, establishing an empirical performance upper-bound for visual reasoning; when the graphs are noisily detected from real-world images, XNMs are still robust to achieve a competitive 67.5% accuracy on VQAv2.0, surpassing the popular bag-of-objects attention models without graph structures.

For agents

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

get_harvested_code_for_paper("1812.01855")
get_code_for_paper("1812.01855")
have("1812.01855")

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

curl https://syntology.ai/api/ran/1812.01855.json

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

[![Syntology run record](https://syntology.ai/api/ran/1812.01855.svg)](https://syntology.ai/paper/1812.01855)

Connect an agent — have() is free.