SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.14972 · ICCV · 2023

Improving Unsupervised Visual Program Inference with Code Rewriting Families

Daniel Ritchie, R Kenny Jones, Aditya Ganeshan

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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2309.14972.json · badge: /api/ran/2309.14972.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
BardOfCodes/coref canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
exists Ran
ran, violated the contract we drafted
BardOfCodes/coref/coref/model/flash_attention.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked. 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. A run is recorded.

once Ran
ran; our contract draft was wrong, not the code
BardOfCodes/coref/coref/model/flash_attention.py
code served (permissive licence) · get_code("52e10a7d6b0fa036")
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 function. 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 functools import wraps

def once(fn):
    called = False

    @wraps(fn)
    def inner(x):
        nonlocal called
        if called:
            return
        called = True
        return fn(x)
    return inner


def sample_function(x):
    """A simple function that the decorator will wrap."""
    return x * 2


ARGS = {
    "fn": sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
preprocess_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BardOfCodes/coref/coref/dataloader/shapes_data.py
code served (permissive licence) · get_code("c2b11afcdad50d08")
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 4, dtype family float, shape (2, 2, 2, 2) 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 as th
import numpy as np

th.manual_seed(0)

# Case 1: 2D input that will be reshaped to 5D
# Shape: (batch=2, features=64) -> reshaped to (2, 4, 4, 4, 1)
data_2d = np.random.randn(2, 64).astype(np.float32)

# Case 2: 5D input directly
# Shape: (batch=2, depth=4, height=3, width=5, channels=1)
data_5d = np.random.randn(2, 4, 3, 5, 1).astype(np.float32)

# Test with 2D data and resolution parameter
resolution = 2

ARGS = {
    "data": data_2d,
    "resolution": resolution
}
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 4, dtype family float, shape (2, 2, 2, 2) — shape (2, 2, 2, 2) 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
shapes_collator Ran
ran; our contract draft was wrong, not the code
BardOfCodes/coref/coref/dataloader/collator.py
code served (permissive licence) · get_code("a5f8557634d228be")
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. 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 as th
th.manual_seed(0)

# The function expects:
# - batch: a list of tuples where each tuple is (occ, key)
#   - occ: array-like that can be converted to tensor
#   - key: sequence that can be joined with '_'
# - device: string for device placement

batch = [
    ([0.1, 0.2, 0.3, 0.4], [1, 2, 3]),
    ([0.5, 0.6, 0.7, 0.8], [4, 5, 6])
]

ARGS = {
    'batch': batch,
    '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 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

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 2 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
exists 486 other papers
224 dated earlier, 6 the same month, 250 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
once 19 other papers
10 dated earlier, 9 later · 4 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2202.01855 (2022-02)
Self-Supervised Learning with Random-Projection Quantizer for Speech Recognition
2203.07852 (2022-03)
Block-Recurrent Transformers
and 16 more not named here

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

Programs offer compactness and structure that makes them an attractive representation for visual data. We explore how code rewriting can be used to improve systems for inferring programs from visual data. We first propose Sparse Intermittent Rewrite Injection (SIRI), a framework for unsupervised bootstrapped learning. SIRI sparsely applies code rewrite operations over a dataset of training programs, injecting the improved programs back into the training set. We design a family of rewriters for visual programming domains: parameter optimization, code pruning, and code grafting. For three shape programming languages in 2D and 3D, we show that using SIRI with our family of rewriters improves performance: better reconstructions and faster convergence rates, compared with bootstrapped learning methods that do not use rewriters or use them naively. Finally, we demonstrate that our family of rewriters can be effectively used at test time to improve the output of SIRI predictions. For 2D and 3D CSG, we outperform or match the reconstruction performance of recent domainspecific neural architectures, while producing more parsimonious programs, that use significantly fewer primitives.

For agents

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

get_harvested_code_for_paper("2309.14972")
get_code_for_paper("2309.14972")
have("2309.14972")

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

curl https://syntology.ai/api/ran/2309.14972.json

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

[![Syntology run record](https://syntology.ai/api/ran/2309.14972.svg)](https://syntology.ai/paper/2309.14972)

Connect an agent — have() is free.