SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.08280 · 2024

Pix2Code: Learning to Compose Neural Visual Concepts as Programs

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 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/2402.08280.json · badge: /api/ran/2402.08280.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/pix2code canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_id Ran
ran, honoured the contract we drafted
ml-research/pix2code/pix2seq/use_model_kandinsky.py
code served (permissive licence) · get_code("9a6ffa77c08d1c89")
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 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 torch
import numpy as np

def get_id(file):
    if 'json' in file:
        return int(file.split('.')[0])
    else:
        file_name = file.split('.')[0]
        return int(file_name.split('_')[-1])

# Test cases to understand the function behavior:
# 1. JSON file: "12345.json" -> splits on '.', takes first part "12345", converts to int 12345
# 2. Non-JSON file: "prefix_67890.txt" -> splits on '.', takes first part "prefix_67890", 
#    splits on '_', takes last part "67890", converts to int 67890

ARGS = {
    'file': '12345.json'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
load_model Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from facebookresearch/productive_concept_learning
pointer only; the stored copy get_code serves, from facebookresearch/productive_concept_learning, is pointer only (licence: NOASSERTION) · get_code("3d4bf01aa4c60523")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

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

FunctionAlso present inEarliest-datedOthers named
load_model 1 other paper
1 dated earlier
2010.02855 (2020-10)
CURI: A Benchmark for Productive Concept Learning Under Uncertainty

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 learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it necessary for human users to be able to understand a model's learnt concepts and potentially revise false behaviours. To tackle both the generalizability and interpretability constraints of visual concept learning, we propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of both explicit, compositional symbolic and implicit neural representations. This is achieved by retrieving object representations from images and synthesizing relational concepts as lambda-calculus programs. We evaluate the diverse properties of Pix2Code on the challenging reasoning domains, Kandinsky Patterns and CURI, thereby testing its ability to identify compositional visual concepts that generalize to novel data and concept configurations. Particularly, in stark contrast to neural approaches, we show that Pix2Code's representations remain human interpretable and can be easily revised for improved performance.

For agents

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

get_harvested_code_for_paper("2402.08280")
get_code_for_paper("2402.08280")
have("2402.08280")

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

curl https://syntology.ai/api/ran/2402.08280.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.08280.svg)](https://syntology.ai/paper/2402.08280)

Connect an agent — have() is free.