SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.04655 · CVPR · 2022

Towards Layer-wise Image Vectorization

Yun Fu, Xu Ma, Yuqian Zhou, Humphrey Shi, Xingqian Xu, Nikita Orlov, Valerii Filev

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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 9 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/2206.04655.json · badge: /api/ran/2206.04655.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
picsart-ai-research/live-layerwise-image-vectorization canonical (classifier label)
classifier basis not recorded on the link
12 ran · 1 no recorded run
FunctionStatusWhere it lives
area Ran
ran, violated the contract we drafted
picsart-ai-research/live-layerwise-image-vectorization/LIVE/xing_loss.py
code served (permissive licence) · get_code("78b8ac06cdb89338")
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 float, ndim 0, dtype family float, 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

torch.manual_seed(0)

# The function area(a, b, c) computes the signed area of a triangle
# using the cross product formula. It accesses:
# - a[1], a[0]: indices 0 and 1 of parameter a
# - b[0], b[1]: indices 0 and 1 of parameter b
# - c[0], c[1]: indices 0 and 1 of parameter c
# So a, b, c need to be indexable sequences with at least 2 elements

a = [1.0, 2.0]
b = [4.0, 5.0]
c = [3.0, 1.0]

ARGS = {
    'a': a,
    'b': b,
    'c': c
}
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 float, ndim 0, dtype family float, 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
compute_sine_theta Ran
ran; our contract draft was wrong, not the code
picsart-ai-research/live-layerwise-image-vectorization/LIVE/xing_loss.py
code served (permissive licence) · get_code("10df26dd8a42e188")
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 0, dtype family float, 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

torch.manual_seed(0)

# The function compute_sine_theta expects two arguments s1 and s2
# Each should be a tensor where:
# - s1[0, :] and s1[1, :] are two points (vectors)
# - s2[0, :] and s2[1, :] are two points (vectors)
# The function computes the sine of the angle between the two direction vectors

# Create two tensors of shape (2, 4) - 2 points with 4 dimensions each
s1 = torch.tensor([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
])

s2 = torch.tensor([
    [0.0, 1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0, 7.0]
])

ARGS = {
    "s1": s1,
    "s2": s2
}
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 Tensor, ndim 0, dtype family float, 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
edict_2_dict Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/LIVE/utils.py
code served (permissive licence) · get_code("acd3411fdfc64cf0")
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
import numpy as np
from collections import OrderedDict

torch.manual_seed(0)

# The function edict_2_dict recursively converts dict-like objects and lists
# into regular dicts and lists. It handles:
# - dict: recursively convert values
# - list: recursively convert elements
# - other types: return as-is

# Construct test data with nested structures
nested_dict = {
    'a': 1,
    'b': 'string',
    'c': torch.tensor([1.0, 2.0, 3.0, 4.0]),
    'd': {
        'nested_key': 42,
        'nested_tensor': torch.randn(2, 4)
    },
    'e': [1, 2, {'inner': 'value'}],
    'f': [torch.tensor([5.0, 6.0]), 'item']
}

ARGS = {
    'x': nested_dict
}
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 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
get_bezier_circle Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/LIVE/colab.py
code served (permissive licence) · get_code("75a57ee84b632625")
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 2, dtype family float, shape (12, 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
import random
import numpy as np

torch.manual_seed(0)
random.seed(0)
np.random.seed(0)

ARGS = {
    "radius": 1,
    "segments": 4,
    "bias": (0.5, 0.3)
}
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 2, dtype family float, shape (12, 2) — shape (12, 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
get_experiment_id Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/LIVE/utils.py
code served (permissive licence) · get_code("26a0540794644302")
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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "debug": 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 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
get_path_schedule Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/LIVE/utils.py
code served (permissive licence) · get_code("38a6557314d9deab")
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, 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
import numpy as np

torch.manual_seed(0)

# Test case 1: 'repeat' type
ARGS_repeat = {
    'type': 'repeat',
    'max_path': 10,
    'schedule_each': 2
}

# Test case 2: 'list' type
ARGS_list = {
    'type': 'list',
    'schedule': [1, 2, 3, 4, 5]
}

# Test case 3: 'exp' type
ARGS_exp = {
    'type': 'exp',
    'base': 2,
    'max_path': 100,
    'max_path_per_iter': 32
}

# Use the 'exp' case as the primary ARGS since it exercises the most logic
ARGS = ARGS_exp
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 list, ndim 1, dtype family int — a list 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
parse_hex Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/DiffVG/pydiffvg/parse_svg.py
code served (permissive licence) · get_code("b6cedb16e0264370")
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 1, dtype family float, shape (3,) 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

torch.manual_seed(0)

def parse_hex(s):
    """
        Hex to tuple
    """
    s = s.lstrip('#')
    if len(s) == 3:
        s = s[0] + s[0] + s[1] + s[1] + s[2] + s[2]
    rgb = tuple((int(s[i:i + 2], 16) for i in (0, 2, 4)))
    return torch.pow(torch.tensor([rgb[0] / 255.0, rgb[1] / 255.0, rgb[2] / 255.0]), 1.0)

ARGS = {
    's': '#FF5733'
}
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 Tensor, ndim 1, dtype family float, shape (3,) — shape (3,) 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
parse_style Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/DiffVG/pydiffvg/parse_svg.py
code served (permissive licence) · get_code("64d11b4cc1d353a1")
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
import matplotlib.colors

torch.manual_seed(0)

# Parse the function signature to identify parameters
# parse_style(s, defs)
# - s: a string containing style definitions separated by semicolons
# - defs: a dictionary for color definitions (used when parsing colors with 'url')

# Create test data for the parameters
test_s = "fill:#FF0000;stroke:rgb(0,255,0);opacity:0.5"

# Create a defs dictionary with some color definitions
test_defs = {
    "mycolor": torch.tensor([1.0, 0.0, 0.0, 1.0]),
    "anothercolor": torch.tensor([0.0, 1.0, 0.0, 1.0])
}

ARGS = {
    "s": test_s,
    "defs": test_defs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, 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
prettify Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/DiffVG/pydiffvg/save_svg.py
code served (permissive licence) · get_code("5470a6bb98bcdefc")
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 str. 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 xml.etree.ElementTree as etree

# Create a simple XML element to pass to prettify
root = etree.Element("root")
child1 = etree.SubElement(root, "child1")
child1.text = "Hello"
child2 = etree.SubElement(root, "child2")
child2.text = "World"
child2.set("attribute", "value")

ARGS = {
    "elem": root
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
remove_namespaces Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/DiffVG/pydiffvg/parse_svg.py
code served (permissive licence) · get_code("e9e71fe574bab40f")
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 str. 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 re

def remove_namespaces(s):
    """
        {...} ... -> ...
    """
    return re.sub('{.*}', '', s)

ARGS = {
    's': '{namespace}some text here'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
triangle_area Ran
ran; our contract draft was wrong, not the code
picsart-ai-research/live-layerwise-image-vectorization/LIVE/xing_loss.py
code served (permissive licence) · get_code("69b23c90ca4b2659")
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 1, dtype family float, shape (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

torch.manual_seed(0)

# Analyze the function:
# - triangle_area(A, B, C) takes three tensor arguments
# - Operations: (C - A).flip([-1]) * (B - A), then indexing with [..., 1] and [..., 0]
# - This suggests A, B, C are tensors with at least 1 dimension
# - The flip([-1]) flips the last dimension
# - The subtraction and multiplication suggest broadcasting-compatible shapes
# - Final indexing [..., 1] and [..., 0] suggests last dimension has at least 2 elements

# For a 2D point (or vector) interpretation:
# - A, B, C should have shape (..., 2) to represent points in 2D
# - Let's use batch size 2, so shape (2, 2) for each

A = torch.tensor([[1.0, 2.0], [3.0, 4.0]])
B = torch.tensor([[5.0, 6.0], [7.0, 8.0]])
C = torch.tensor([[9.0, 10.0], [11.0, 12.0]])

ARGS = {
    "A": A,
    "B": B,
    "C": C,
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (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
ycrcb_conversion Ran
ran on a synthesized input
picsart-ai-research/live-layerwise-image-vectorization/LIVE/colab.py
code served (permissive licence) · get_code("526a52340d5b84dc")
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 (2, 3, 4, 4) 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

torch.manual_seed(0)

# Create a small image tensor with shape [bs x 3 x 2D]
# bs=2 (batch size), 3 channels, 4x4 spatial dimensions
im_bs_3_2d = torch.randn(2, 3, 4, 4)

# Create a small 2D image tensor with shape [2D x 3]
# Flattened spatial dimensions: 16 pixels, 3 channels
im_2d_3 = torch.randn(16, 3)

ARGS = {
    'im': im_bs_3_2d,
    'format': '[bs x 3 x 2D]',
    'reverse': 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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 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
get_sdf Not yet run
unverified (harvested, no recorded run)
picsart-ai-research/live-layerwise-image-vectorization/LIVE/colab.py
code served (permissive licence) · get_code("20a081b681345e70")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 10 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
compute_sine_theta 2 other papers
2 later
aaai_27987 (2024 (year only))
Optimize & Reduce: A Top-Down Approach for Image Vectorization
2408.15741 (2024-08)
Segmentation-guided Layer-wise Image Vectorization with Gradient Fills
area 1 other paper
1 later
2312.16476 (2023-12)
SVGDreamer: Text Guided SVG Generation with Diffusion Model
triangle_area 1 other paper
1 later
2312.16476 (2023-12)
SVGDreamer: Text Guided SVG Generation with Diffusion Model

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

Layer-wise Image Vectorization (from left to right) Figure 1. Examples of the learning course of our Layer-wise Image Vectorization. The proposed method can reconstruct the image in a layer-wise coarse-to-fine manner with only few paths. "N" indicates the path number.

For agents

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

get_harvested_code_for_paper("2206.04655")
get_code_for_paper("2206.04655")
have("2206.04655")

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

curl https://syntology.ai/api/ran/2206.04655.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.04655.svg)](https://syntology.ai/paper/2206.04655)

Connect an agent — have() is free.