SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.02500 · 2023

Systematic Visual Reasoning through Object-Centric Relational Abstraction

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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, 1 violated it and 2 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/2306.02500.json · badge: /api/ran/2306.02500.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
shanka123/ocra canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
build_grid Ran
ran; our contract draft was wrong, not the code
shanka123/ocra/ocra.py
code served (permissive licence) · get_code("a894bb5fa452ee7b")
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 Tensor, ndim 4, dtype family float, shape (1, 4, 3, 4) as a later run recorded it. 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, 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 numpy as np
import torch

torch.manual_seed(0)

ARGS = {
    "resolution": [4, 3]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (1, 4, 3, 4) — shape (1, 4, 3, 4) 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
fill_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shanka123/ocra/train_ocra_dist3.py
code served (permissive licence) · get_code("f133741b878deb4f")
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 ndarray, ndim 2, dtype family float, shape (20, 20) 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 numpy as np

torch.manual_seed(0)

# Create a list of small images with different dimensions to test the parity logic
all_imgs = [
    np.random.rand(4, 3).astype(np.float32),  # even height, odd width
    np.random.rand(3, 4).astype(np.float32),  # odd height, even width
    np.random.rand(3, 3).astype(np.float32),  # odd height, odd width
    np.random.rand(4, 4).astype(np.float32),  # even height, even width
]

# Index to select which image to fill
idx = 0

# Full image canvas - needs to be large enough to accommodate placement at point p
full_img = np.zeros((20, 20), dtype=np.float32)

# Point p where the image should be centered
p = [10, 10]

ARGS = {
    "all_imgs": all_imgs,
    "idx": idx,
    "full_img": full_img,
    "p": p,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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 (20, 20) — shape (20, 20) 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
full_dset Ran
ran on a synthesized input
shanka123/ocra/RMTS.py
code served (permissive licence) · get_code("78eeda7b80184c98")
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

# Set random seed for reproducibility
np.random.seed(0)

# The function takes two parameters: shapes and n_trials
# shapes: appears to be a list/iterable of shape identifiers (used in combinations)
# n_trials: an integer specifying the number of trials to return

# Looking at the function body:
# - shapes is used with combinations(shapes, 4) and combinations(shapes, 5)
# - Each element of shapes is used as an identifier (removed, appended to lists)
# - The function constructs sequences of length 6 from 4 shapes (same_seq) 
#   or length 6 from 5 shapes (diff_seq)
# - n_trials is used to determine dataset size

# Minimal valid shapes: list of distinct identifiers
# We need at least 5 unique shapes for the combinations(shapes, 5) to work
shapes = [0, 1, 2, 3, 4]

# n_trials: a reasonable number for dataset size
n_trials = 100

ARGS = {
    "shapes": shapes,
    "n_trials": n_trials,
}
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
n_comb Ran
ran on a synthesized input
shanka123/ocra/RMTS.py
code served (permissive licence) · get_code("bdd3b58e7621b3a1")
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 int, ndim 0, dtype family int, shape () 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 math

def n_comb(n, r):
    return int(math.factorial(n) / (math.factorial(r) * math.factorial(n - r)))

ARGS = {
    "n": 5,
    "r": 2
}
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 int, ndim 0, dtype family int, shape () — shape () 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
pair Ran
ran, violated the contract we drafted
shanka123/ocra/ocra.py
code served (permissive licence) · get_code("6ba8cee9f5daea41")
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) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# The function 'pair' takes a single parameter 't' and returns it as a tuple if it isn't already one
# We need to test both cases: when t is a tuple and when it's not

# Case 1: t is not a tuple (e.g., an integer, string, tensor, etc.)
t_not_tuple = 5

# Case 2: t is already a tuple
t_is_tuple = (3, 7)

# We'll use the non-tuple case as the primary test
ARGS = {
    "t": t_not_tuple
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
subsampled_dset Not yet run
unverified (harvested, no recorded run)
shanka123/ocra/RMTS.py
code served (permissive licence) · get_code("6f935152f1bb9df2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 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.

FunctionAlso present inEarliest-datedOthers named
pair 90 other papers
31 dated earlier, 1 the same month, 55 later, 2 same year, order not determinable, 1 undated · 8 only as an assembly brick
2004.13649 (2020-04)
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2103.15691 (2021-03)
ViViT: A Video Vision Transformer
and 87 more not named here
build_grid 2 other papers
1 dated earlier, 1 later
2303.02260 (2023-03)
Learning to reason over visual objects
2403.03458 (2024-03)
Slot Abstractors: Toward Scalable Abstract Visual Reasoning
fill_image 1 other paper
1 later
2403.03458 (2024-03)
Slot Abstractors: Toward Scalable Abstract Visual Reasoning

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

Human visual reasoning is characterized by an ability to identify abstract patterns from only a small number of examples, and to systematically generalize those patterns to novel inputs. This capacity depends in large part on our ability to represent complex visual inputs in terms of both objects and relations. Recent work in computer vision has introduced models with the capacity to extract object-centric representations, leading to the ability to process multi-object visual inputs, but falling short of the systematic generalization displayed by human reasoning. Other recent models have employed inductive biases for relational abstraction to achieve systematic generalization of learned abstract rules, but have generally assumed the presence of object-focused inputs. Here, we combine these two approaches, introducing Object-Centric Relational Abstraction (OCRA), a model that extracts explicit representations of both objects and abstract relations, and achieves strong systematic generalization in tasks (including a novel dataset, CLEVR-ART, with greater visual complexity) involving complex visual displays.

For agents

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

get_harvested_code_for_paper("2306.02500")
get_code_for_paper("2306.02500")
have("2306.02500")

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

curl https://syntology.ai/api/ran/2306.02500.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.02500.svg)](https://syntology.ai/paper/2306.02500)

Connect an agent — have() is free.