SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.04127 · CVPR · 2022

HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video

Ira Kemelmacher-Shlizerman, Jonathan Barron, Brian Curless, Pratul Srinivasan, Chung-Yi Weng

arXiv · PDF · Open in the Atlas

Code that ran

11 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; 1 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 1 failure of our instrument; 2 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/2201.04127.json · badge: /api/ran/2201.04127.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
chungyiweng/humannerf canonical (classifier label)
classifier basis not recorded on the link
11 ran · 2 no recorded run
FunctionStatusWhere it lives
body_pose_to_body_RTs Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/body_util.py
code served (permissive licence) · get_code("1f398d8da6e963d6")
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 up the arguments for body_pose_to_body_RTs
jangles = np.random.randn(24, 3).astype('float32')  # 24 joints, 3 angles each
tpose_joints = np.random.randn(24, 3).astype('float32')  # 24 joints in T-pose, 3D coordinates

ARGS = {
    'jangles': jangles,
    'tpose_joints': tpose_joints
}
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
cpu_data_to_gpu Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/train_util.py
code served (permissive licence) · get_code("959a09e5c1edaefb")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a valid cpu_data dict with various tensor types
cpu_data = {
    "tensor_single": torch.randn(2, 4),
    "tensor_list": [torch.randn(2, 4), torch.randn(3, 5)],
    "tensor_dict": {"key1": torch.randn(2, 4), "key2": torch.randn(3, 5)},
    "string_list": ["hello", "world"],
    "exclude_me": torch.randn(2, 4),
}

exclude_keys = ["exclude_me"]

ARGS = {
    "cpu_data": cpu_data,
    "exclude_keys": exclude_keys,
}
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
get_camrot Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/camera_util.py
code served (permissive licence) · get_code("32ab0b025a8f3a9f")
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 (3, 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 numpy as np

# Camera position in 3D space
campos = np.array([1.0, 2.0, 3.0], dtype=np.float32)

# Point the camera is looking at
lookat = np.array([0.0, 0.0, 0.0], dtype=np.float32)

# Whether to invert the camera (flip up vector)
inv_camera = False

ARGS = {
    "campos": campos,
    "lookat": lookat,
    "inv_camera": inv_camera
}
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 ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 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
get_canonical_global_tfms Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/body_util.py
code served (permissive licence) · get_code("7cd3b02b1907c453")
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 3, dtype family float, shape (24, 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 numpy as np

# Construct canonical_joints as a (24, 3) array representing SMPL joint positions
# 24 is the standard number of SMPL joints
canonical_joints = np.array([
    [0.0, 0.0, 0.0],      # 0: root
    [0.1, 0.2, 0.3],      # 1
    [-0.1, 0.2, 0.3],     # 2
    [0.0, -0.2, 0.1],     # 3
    [0.15, 0.4, 0.5],     # 4
    [-0.15, 0.4, 0.5],    # 5
    [0.0, -0.4, 0.2],     # 6
    [0.2, 0.6, 0.7],      # 7
    [-0.2, 0.6, 0.7],     # 8
    [0.0, -0.6, 0.3],     # 9
    [0.25, 0.8, 0.9],     # 10
    [0.0, -0.8, 0.4],     # 11
    [0.3, 1.0, 1.1],      # 12
    [-0.3, 1.0, 1.1],     # 13
    [0.0, -1.0, 0.5],     # 14
    [0.35, 1.2, 1.3],     # 15
    [0.33, 1.05, 1.15],   # 16
    [0.36, 1.25, 1.35],   # 17
    [0.34, 1.1, 1.2],     # 18
    [0.37, 1.3, 1.4],     # 19
    [0.35, 1.15, 1.25],   # 20
    [0.38, 1.35, 1.45],   # 21
    [-0.35, 1.2, 1.3],    # 22
    [-0.33, 1.05, 1.15],  # 23
], dtype='float32')

ARGS = {
    'canonical_joints': canonical_joints,
}
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 ndarray, ndim 3, dtype family float, shape (24, 4, 4) — shape (24, 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
list_files Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/file_util.py
code served (permissive licence) · get_code("eec396c82b5e42bd")
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 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 os
import tempfile
import shutil

# Create a temporary directory with some test files
temp_dir = tempfile.mkdtemp()

# Create some test files
open(os.path.join(temp_dir, "file1.txt"), "w").close()
open(os.path.join(temp_dir, "file2.py"), "w").close()
open(os.path.join(temp_dir, "file3.txt"), "w").close()
open(os.path.join(temp_dir, "data_test.csv"), "w").close()
open(os.path.join(temp_dir, "other.json"), "w").close()

# Define arguments for the function
ARGS = {
    "folder_path": temp_dir,
    "exts": [".txt", ".py"],
    "keyword": "file"
}
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 list, ndim 1, dtype family float — 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
load_image Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/image_util.py
code served (permissive licence) · get_code("dc4348e81c92f172")
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 Image. 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 tempfile
from PIL import Image
import os

# Create a temporary directory and a test image
temp_dir = tempfile.mkdtemp()
test_image_path = os.path.join(temp_dir, "test_image.png")

# Create a small test image (4x3 pixels, RGB)
test_img = Image.new('RGB', (4, 3), color=(255, 0, 0))
test_img.save(test_image_path)

ARGS = {
    "path": test_image_path,
    "to_rgb": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
rotate_camera_by_frame_idx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chungyiweng/humannerf/core/utils/camera_util.py
code served (permissive licence) · get_code("59b04ecdb5519178")
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 (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 numpy as np
import cv2

# Create extrinsics as a 4x4 matrix (homogeneous transformation matrix)
# Starting with identity and slight perturbations to make it realistic
extrinsics = np.array([
    [0.9, -0.1, 0.0, 1.0],
    [0.1, 0.9, 0.0, 2.0],
    [0.0, 0.0, 1.0, 3.0],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

# Frame index - an integer
frame_idx = 5

# Translation vector - optional, can be None or a 3-element array
trans = np.array([0.5, 0.2, 0.1], dtype=np.float32)

# Rotation axis - one of 'x', 'y', 'z'
rotate_axis = 'y'

# Period - number of frames for one full rotation
period = 196

# inv_angle - boolean flag for clockwise/counterclockwise
inv_angle = False

ARGS = {
    'extrinsics': extrinsics,
    'frame_idx': frame_idx,
    'trans': trans,
    'rotate_axis': rotate_axis,
    'period': period,
    'inv_angle': inv_angle
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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 (4, 4) — shape (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
split_path Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/file_util.py
code served (permissive licence) · get_code("dd6fb7e4e7403610")
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 os

def split_path(file_path):
    file_dir, file_name = os.path.split(file_path)
    file_base_name, file_ext = os.path.splitext(file_name)
    return (file_dir, file_base_name, file_ext)

ARGS = {
    "file_path": "/home/user/documents/example.txt"
}
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 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
to_3ch_image Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/image_util.py
code served (permissive licence) · get_code("3f0b3baff715cca9")
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 3, dtype family float, shape (4, 5, 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 numpy as np

# Test case 1: 2D grayscale image (H, W)
image_2d = np.random.rand(4, 5).astype(np.float32)

# Test case 2: 3D grayscale image with channel dimension (H, W, 1)
image_3d = np.random.rand(4, 5, 1).astype(np.float32)

# Use the 2D case as the main argument
ARGS = {
    "image": image_2d
}
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 ndarray, ndim 3, dtype family float, shape (4, 5, 3) — shape (4, 5, 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
to_8b_image Ran
ran on a synthesized input
chungyiweng/humannerf/core/utils/image_util.py
code served (permissive licence) · get_code("4ce6f546fc3de91a")
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 3, dtype family int, shape (2, 2, 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 numpy as np

# The function to_8b_image takes an image parameter
# It clips values to [0, 1] range and scales to [0, 255], converting to uint8
# The parameter should be a numpy array or array-like with float values

# Create a small test image with float values in range [0, 1]
test_image = np.array([
    [[0.0, 0.5, 1.0, 0.25],
     [0.75, 0.1, 0.9, 0.3]],
    [[0.2, 0.8, 0.4, 0.6],
     [0.15, 0.85, 0.05, 0.95]]
], dtype=np.float32)

ARGS = {
    "image": test_image
}
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 ndarray, ndim 3, dtype family int, shape (2, 2, 4) — shape (2, 2, 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
xaviermultiplier Ran
ran, honoured the contract we drafted
chungyiweng/humannerf/core/utils/network_util.py
code served (permissive licence) · get_code("083a34412fafa799")
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 torch.nn as nn
import math

torch.manual_seed(0)

# Test with Conv1d
m_conv1d = nn.Conv1d(in_channels=3, out_channels=16, kernel_size=5)
gain_value = 1.0

ARGS = {
    "m": m_conv1d,
    "gain": gain_value,
}
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 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
apply_global_tfm_to_camera Not yet run
unverified (harvested, no recorded run)
chungyiweng/humannerf/core/utils/camera_util.py
code served (permissive licence) · get_code("f249cc2f90918ffc")
How it ran

no invocation recorded.

approx_gaussian_bone_volumes Not yet run
unverified (harvested, no recorded run)
chungyiweng/humannerf/core/utils/body_util.py
code served (permissive licence) · get_code("b9975db84fddfe95")
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, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 9 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
rotate_camera_by_frame_idx 2 other papers
2 later
2312.02134 (2023-12)
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
2404.07991 (2024-04)
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
xaviermultiplier 2 other papers
2 later
2312.02973 (2023-12)
GauHuman: Articulated Gaussian Splatting from Monocular Human Videos
2503.14198 (2025-03)
RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
list_files 1 other paper
1 later
2404.07991 (2024-04)
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
split_path 1 other paper
1 later
2404.07991 (2024-04)
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh

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

Figure 1. Our method takes as input a monocular video 1 of a human performing complex movement, e.g., dancing (left), and creates a free-viewpoint rendering for any frame in the sequence (right). We construct a canonical subject appearance volume, and a motion field mapping from observation to canonical space, trained on the video. At test time, we take just the pose from the source frame (red square) and synthesize all output views, including the target view. Please refer to the project page 2 to see the animated results.

For agents

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

get_harvested_code_for_paper("2201.04127")
get_code_for_paper("2201.04127")
have("2201.04127")

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

curl https://syntology.ai/api/ran/2201.04127.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.04127.svg)](https://syntology.ai/paper/2201.04127)

Connect an agent — have() is free.