SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.14092 · CVPR · 2023

NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images

Di Huang, Haiyu Zhang, Hongyu Yang, Mingwu Zheng

arXiv · PDF · Open in the Atlas

Code that ran

10 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, 0 violated it and 1 has no contract verdict; 9 failures of our instrument; 3 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/2303.14092.json · badge: /api/ran/2303.14092.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
aejion/neuface canonical (classifier label)
classifier basis not recorded on the link
10 ran · 3 no recorded run
FunctionStatusWhere it lives
divergence Ran
ran; our contract draft was wrong, not the code
aejion/neuface/models/diff_opts.py
code served (permissive licence) · get_code("87e822f4bcfbdac7")
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 (2, 1) 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 divergence function computes the divergence of a vector field y with respect to x
# It requires:
# - y: a tensor with shape [..., n] where n is the output dimension
# - x: a tensor that y depends on, requires grad

# Create a small input tensor x with requires_grad=True
x = torch.randn(2, 4, requires_grad=True)

# Create y as a function of x
# y should have shape [..., output_dim]
# We'll create y with output dimension 3 (distinct from input dim 4)
# y = some function of x, e.g., a simple linear-like transformation
y = torch.sum(x, dim=1, keepdim=True) * torch.ones(2, 3)
y.requires_grad_(True)

# Alternatively, if y needs to be explicitly computed from x:
# Let's make y depend on x through autograd graph
y = x[:, :3] * 2.0 + x[:, 1:4].sum(dim=1, keepdim=True)

ARGS = {
    "y": y,
    "x": x,
}
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 2, dtype family float, shape (2, 1) — shape (2, 1) 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
frequency_init Ran
ran; our contract draft was wrong, not the code
aejion/neuface/models/modules.py
code served (permissive licence) · get_code("1bb72e25164f7f07")
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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# The function frequency_init takes a freq parameter (a frequency scalar)
# and returns an initialization function that can be applied to nn.Module instances.
# The init function modifies Linear layers by uniformly initializing their weights.

# Build a small model to test the initialization
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# freq parameter: a positive number that scales the initialization range
freq = 2.0

ARGS = {
    "freq": freq
}
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 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
frequency_init Ran
ran; our contract draft was wrong, not the code
aejion/neuface/render_model/film.py
code served (permissive licence) · get_code("69c8c97f5b9d10b6")
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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# The frequency_init function takes a freq parameter (a number)
# and returns an init function that can be applied to nn.Module instances.
# The init function modifies Linear layer weights uniformly based on the frequency.

# Create a simple neural network to demonstrate the initialization
model = nn.Sequential(
    nn.Linear(4, 3),
    nn.Linear(3, 2)
)

# freq is a numeric parameter that scales the initialization range
freq = 2.0

ARGS = {
    "freq": freq
}
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 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
get_embedder Ran
ran; our contract draft was wrong, not the code
aejion/neuface/render_model/embedder.py
code served (permissive licence) · get_code("40caf9fbfe050a14")
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, ndim 1, dtype family float; 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)

ARGS = {
    'multires': 4
}
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 tuple, ndim 1, dtype family float — 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
get_subdict Ran
ran; our contract draft was wrong, not the code
aejion/neuface/models/modules.py
code served (permissive licence) · get_code("610a630c654d9d50")
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 OrderedDict. 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 collections import OrderedDict

torch.manual_seed(0)

# Analyze the function:
# - get_subdict takes a dictionary and an optional key parameter
# - It returns None if dictionary is None
# - It returns the full dictionary if key is None or empty string
# - Otherwise it filters the dictionary by keys matching a regex pattern
# The function uses:
#   - dictionary.items() - so it needs to be dict-like
#   - key parameter for regex matching

# Test case 1: Full dictionary with key filtering
test_dict = OrderedDict([
    ('model.layer1.weight', torch.randn(2, 4)),
    ('model.layer1.bias', torch.randn(4)),
    ('model.layer2.weight', torch.randn(3, 2)),
    ('optimizer.lr', 0.001),
    ('model.layer2.bias', torch.randn(3)),
])

test_key = 'model.layer1'

ARGS = {
    'dictionary': test_dict,
    'key': test_key,
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
hessian Ran
ran; our contract draft was wrong, not the code
aejion/neuface/models/diff_opts.py
code served (permissive licence) · get_code("fd089b9f4b8749ab")
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 torch
torch.manual_seed(0)

# The function expects:
# y: shape (meta_batch_size, num_observations, channels)
# x: shape (meta_batch_size, num_observations, 2)
# Both need to require grad for autograd to work

meta_batch_size = 2
num_observations = 3
channels = 4
x_dim = 2

# x needs to be differentiable
x = torch.randn(meta_batch_size, num_observations, x_dim, requires_grad=True, dtype=torch.float32)

# y should be a function of x to compute meaningful gradients
# Create a simple function: y = x^2 summed in a way that gives us channels outputs
y = torch.sum(x.unsqueeze(-1) ** 2, dim=2)  # shape (meta_batch_size, num_observations, 1)
y = y.expand(meta_batch_size, num_observations, channels)  # expand to (meta_batch_size, num_observations, channels)
y.requires_grad_(True)

ARGS = {
    "y": y,
    "x": x,
}
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 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
laplace Ran
ran; our contract draft was wrong, not the code
aejion/neuface/models/diff_opts.py
code served (permissive licence) · get_code("a2be4be6558869af")
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 (2, 1) 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 tensor y that depends on x via autograd graph
# y needs to have a last dimension so we can iterate over it in divergence()
# Shape: (batch=2, feature_dim=4)
x = torch.randn(2, 4, dtype=torch.float32, requires_grad=True)

# Create y as a function of x so the autograd graph is built
# y should also have shape compatible with the divergence function
# We'll make y = x^2 to create a simple dependency
y = (x ** 2).sum(dim=1, keepdim=True)  # Shape: (2, 1)

ARGS = {
    "y": y,
    "x": x,
}
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 2, dtype family float, shape (2, 1) — shape (2, 1) 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
positional_encoding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aejion/neuface/models/modules.py
code served (permissive licence) · get_code("70c30e0b345fa518")
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 (2, 52) 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 input tensor
# Shape: (batch_size=2, feature_dim=4)
tensor = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "tensor": tensor,
    "num_encoding_functions": 6,
    "include_input": True,
    "log_sampling": True,
}
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 2, dtype family float, shape (2, 52) — shape (2, 52) 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
rp_to_se3 Ran
ran; our contract draft was wrong, not the code
aejion/neuface/models/rigid.py
code served (permissive licence) · get_code("c0c5326e8e629cc5")
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, 4, 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 small test tensors matching the function signature
B = 2  # batch size
N = 4  # number of transforms
D = 3  # rotation matrix dimension

# R: (B, N, 3, 3) - orthonormal rotation matrices
# Using identity matrices as valid rotations
R = torch.eye(3).unsqueeze(0).unsqueeze(0).repeat(B, N, 1, 1)

# p: (B, N, 3) - translation vectors
p = torch.randn(B, N, 3)

ARGS = {
    "R": R,
    "p": p,
}
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, 4, 4, 4) — shape (2, 4, 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
sample_from_3dgrid Ran
ran on a synthesized input
aejion/neuface/render_model/film.py
code served (permissive licence) · get_code("4139e1fcfcbad38d")
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 3, dtype family float, shape (2, 4, 8) 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)

# Construct coordinates tensor
# Shape: (batch_size, num_points_per_batch, 3)
batch_size = 2
num_points_per_batch = 4
coordinates = torch.randn(batch_size, num_points_per_batch, 3)

# Construct grid tensor
# Shape: (1, channels, H, W, D)
channels = 8
H, W, D = 5, 6, 7
grid = torch.randn(1, channels, H, W, D)

ARGS = {
    "coordinates": coordinates,
    "grid": grid,
}
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 3, dtype family float, shape (2, 4, 8) — shape (2, 4, 8) 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
e3_SH Not yet run
unverified (harvested, no recorded run)
aejion/neuface/render_model/render_network.py
code served (permissive licence) · get_code("54f404676640c282")
How it ran

no invocation recorded.

exp_so3 Not yet run
unverified (harvested, no recorded run)
aejion/neuface/models/rigid.py
code served (permissive licence) · get_code("87c8d69a40a056bb")
How it ran

no invocation recorded.

skew Not yet run
unverified (harvested, no recorded run)
aejion/neuface/models/rigid.py
code served (permissive licence) · get_code("e6f8890cd2ea2b39")
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 12 distinct functions with an identity, 10 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 9 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
laplace 6 other papers
3 dated earlier, 3 later
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2007.09601 (2020-07)
Hypersolvers: Toward Fast Continuous-Depth Models
2108.08478 (2021-08)
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
and 3 more not named here
get_embedder 5 other papers
4 dated earlier, 1 later
2003.09852 (2020-03)
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
2104.03953 (2021-04)
SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes
2112.07471 (2021-12)
I M Avatar: Implicit Morphable Head Avatars from Videos
and 2 more not named here
divergence 4 other papers
2 dated earlier, 2 later
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2108.08478 (2021-08)
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations
and 1 more not named here
get_subdict 3 other papers
1 dated earlier, 2 later
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2310.05174 (2023-10)
GSLB: The Graph Structure Learning Benchmark
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations
hessian 3 other papers
2 dated earlier, 1 later
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2108.08478 (2021-08)
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations
exp_so3 1 other paper
1 later
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations
frequency_init 1 other paper
1 dated earlier
2207.10257 (2022-07)
Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
positional_encoding 1 other paper
1 later
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations
rp_to_se3 1 other paper
1 later
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations
skew 1 other paper
1 later
2312.04028 (2023-12)
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations

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

Realistic face rendering from multi-view images is beneficial to various computer vision and graphics applications. Due to complex spatially-varying reflectance properties and geometry characteristics of faces, however, it remains challenging to recover 3D facial representations both faithfully and efficiently in the current studies. This paper presents a novel 3D face rendering model, namely NeuFace, to learn accurate and physically-meaningful underlying 3D representations by neural rendering techniques. It naturally incorporates the neural BRDFs into physically based rendering, capturing sophisticated facial geometry and appearance clues in a collaborative manner. Specifically, we introduce an approximated BRDF integration and a simple yet new low-rank prior, which effectively lower the ambiguities and boost the performance of the facial BRDFs. Extensive experiments are performed to demonstrate the superiority of NeuFace in human face rendering, along with a decent generalization ability to common objects. Code is released at NeuFace.

For agents

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

get_harvested_code_for_paper("2303.14092")
get_code_for_paper("2303.14092")
have("2303.14092")

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

curl https://syntology.ai/api/ran/2303.14092.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.14092.svg)](https://syntology.ai/paper/2303.14092)

Connect an agent — have() is free.