SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.02833 · ICCV · 2021

Elaborative Rehearsal for Zero-shot Action Recognition

Dong Huang, Shizhe Chen

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 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 6 have no contract verdict; 3 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2108.02833.json · badge: /api/ran/2108.02833.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
DeLightCMU/ElaborativeRehearsal canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
build_scheduler Ran
ran on a synthesized input
DeLightCMU/ElaborativeRehearsal/framework/lr_helper.py
code served (permissive licence) · get_code("75baaf5e487ddd3b")
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 ChainIterLR. 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 torch.optim as optim

torch.manual_seed(0)

# Build a minimal model for the optimizer
model = nn.Linear(4, 3)

# Build an optimizer
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Build cfg_scheduler dict
cfg_scheduler = {
    'warmup_type': 'linear',
    'warmup_iter': 10,
    'type': None,  # Will use ConstantLRScheduler
    'kwargs': {}
}

# Set parameters
base_lr = 0.1
batch_size = 2

ARGS = {
    'cfg_scheduler': cfg_scheduler,
    'optimizer': optimizer,
    'base_lr': base_lr,
    'batch_size': batch_size
}
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 ChainIterLR — a ChainIterLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ChainIterLR 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
DeLightCMU/ElaborativeRehearsal/bit_pytorch/models.py
code served (permissive licence) · get_code("ee80cf467065076b")
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 StdConv2d. 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

torch.manual_seed(0)

ARGS = {
    'cin': 3,
    'cout': 16,
    'stride': 1,
    'bias': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type StdConv2d — a StdConv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StdConv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
DeLightCMU/ElaborativeRehearsal/bit_pytorch/models.py
code served (permissive licence) · get_code("f01b8d3901f0b289")
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 StdConv2d. 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

torch.manual_seed(0)

ARGS = {
    'cin': 3,
    'cout': 16,
    'stride': 1,
    'groups': 1,
    'bias': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type StdConv2d — a StdConv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StdConv2d 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_mixup Ran
ran on a synthesized input
DeLightCMU/ElaborativeRehearsal/bit_pytorch/bit_hyperrule.py
code served (permissive licence) · get_code("7d63034d0bfadd78")
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 get_mixup takes dataset_size as a parameter
# It returns 0.0 if dataset_size < 20000, else 0.1
# We need to construct a valid dataset_size argument

# Test with a small dataset size (less than 20000)
dataset_size_small = 15000

# Test with a large dataset size (>= 20000)
dataset_size_large = 25000

# We can use either one; let's use the large one to test the else branch
ARGS = {
    "dataset_size": 25000
}
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
get_resolution Ran
ran on a synthesized input
DeLightCMU/ElaborativeRehearsal/bit_pytorch/bit_hyperrule.py
code served (permissive licence) · get_code("a933bb17fdb8ebb4")
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 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

torch.manual_seed(0)

# The function takes original_resolution as a parameter
# It expects a tuple or sequence with at least 2 elements (H, W)
# It accesses original_resolution[0] and original_resolution[1]
# and performs multiplication and comparison operations

ARGS = {
    "original_resolution": (100, 100)
}
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 int — 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_resolution_from_dataset Ran
ran on a synthesized input
DeLightCMU/ElaborativeRehearsal/bit_pytorch/bit_hyperrule.py
code served (permissive licence) · get_code("53256b67d70b0daf")
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 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

ARGS = {
    'dataset': 'cifar10'
}
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 int — 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
reduce_dict Ran
ran; our contract draft was wrong, not the code
DeLightCMU/ElaborativeRehearsal/framework/dist_helper.py
code served (permissive licence) · get_code("5b2ec24a42ad7b48")
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 torch.distributed as dist

torch.manual_seed(0)

# Create a simple input dict with scalar tensors
# The function expects all values to be scalar CUDA tensors, but since we're CPU-only,
# we'll pass CPU tensors and let the function handle it
input_dict = {
    "loss": torch.tensor(0.5),
    "accuracy": torch.tensor(0.95),
    "mse": torch.tensor(0.1)
}

ARGS = {
    "input_dict": input_dict,
    "average": 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 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
set_logger Ran
ran on a synthesized input
DeLightCMU/ElaborativeRehearsal/framework/log_helper.py
code served (permissive licence) · get_code("74be527286b869a4")
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 Logger. 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 os
import tempfile
import shutil

# Create a temporary directory for the test
temp_dir = tempfile.mkdtemp()

# Define the log file path (file should not exist yet)
log_file_path = os.path.join(temp_dir, 'test_log.txt')

ARGS = {
    'log_path': log_file_path,
    'log_name': 'training'
}

# Clean up after potential runs
def cleanup():
    if os.path.exists(temp_dir):
        shutil.rmtree(temp_dir)
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
setup_logger Ran
ran on a synthesized input
DeLightCMU/ElaborativeRehearsal/bit_pytorch/bit_common.py
code served (permissive licence) · get_code("12323f0640436acc")
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 Logger. 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 logging.config
import os
import tempfile

# Create a temporary directory for logging
temp_logdir = tempfile.mkdtemp()

# Create a simple args class with the required attributes
class Args:
    def __init__(self, logdir, name):
        self.logdir = logdir
        self.name = name

ARGS = {
    "args": Args(logdir=temp_logdir, name="test_run")
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
tf2th Ran
ran, violated the contract we drafted
DeLightCMU/ElaborativeRehearsal/bit_pytorch/models.py
code served (permissive licence) · get_code("7023eb86801bb3a3")
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 (6, 5, 3, 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
import numpy as np

torch.manual_seed(0)

# Create a 4D numpy array in HWIO format (Height, Width, Input channels, Output channels)
# Using distinct dimensions: H=3, W=4, I=5, O=6
conv_weights = np.random.randn(3, 4, 5, 6).astype(np.float32)

ARGS = {
    "conv_weights": conv_weights
}
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 4, dtype family float, shape (6, 5, 3, 4) — shape (6, 5, 3, 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
all_gather Not yet run
unverified (harvested, no recorded run)
DeLightCMU/ElaborativeRehearsal/framework/dist_helper.py
code served (permissive licence) · get_code("9add02470de77597")
How it ran

no invocation recorded.

create_dat Not yet run
unverified (harvested, no recorded run)
DeLightCMU/ElaborativeRehearsal/bit_pytorch/lbtoolbox.py
code served (permissive licence) · get_code("d38eeb648f68f197")
How it ran

no invocation recorded.

gather Not yet run
unverified (harvested, no recorded run)
DeLightCMU/ElaborativeRehearsal/framework/dist_helper.py
code served (permissive licence) · get_code("842ad4fd53da0aec")
How it ran

no invocation recorded.

gather_data Not yet run
unverified (harvested, no recorded run)
DeLightCMU/ElaborativeRehearsal/bit_pytorch/extract_bit_feature.py
code served (permissive licence) · get_code("bb1e7543d149c2a6")
How it ran

no invocation recorded.

load_dat Not yet run
unverified (harvested, no recorded run)
DeLightCMU/ElaborativeRehearsal/bit_pytorch/lbtoolbox.py
code served (permissive licence) · get_code("12109eac56e48b6b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 12 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 12 later) and 3 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
conv1x1 33 other papers
6 dated earlier, 1 the same month, 26 later · 3 only as an assembly brick
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2102.04306 (2021-02)
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
and 30 more not named here
conv3x3 33 other papers
6 dated earlier, 1 the same month, 26 later · 3 only as an assembly brick
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2102.04306 (2021-02)
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
and 30 more not named here
tf2th 17 other papers
3 dated earlier, 14 later
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2104.02610 (2021-04)
On the Robustness of Vision Transformers to Adversarial Examples
2106.01127 (2021-06)
Towards Robust Classification Model by Counterfactual and Invariant Data Generation
and 14 more not named here
all_gather 16 other papers
16 later
136730727 (2022 (year only))
Self-Supervised Sparse Representation for Video Anomaly Detection
2023.findings-emnlp.644 (2023 (year only))
VIP5: Towards Multimodal Foundation Models for Recommendation
and 13 more not named here
reduce_dict 15 other papers
2 dated earlier, 13 later
2003.04030 (2020-03)
Learning Delicate Local Representations for Multi-Person Pose Estimation
2004.01946 (2020-04)
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
136730727 (2022 (year only))
Self-Supervised Sparse Representation for Video Anomaly Detection
and 12 more not named here
gather 14 other papers
14 later
136730727 (2022 (year only))
Self-Supervised Sparse Representation for Video Anomaly Detection
2023.findings-emnlp.644 (2023 (year only))
VIP5: Towards Multimodal Foundation Models for Recommendation
and 11 more not named here
create_dat 4 other papers
4 later
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
and 1 more not named here
get_mixup 4 other papers
4 later
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
and 1 more not named here
load_dat 4 other papers
4 later
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
and 1 more not named here
get_resolution 3 other papers
3 later
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
2303.13995 (2023-03)
LINe: Out-of-Distribution Detection by Leveraging Important Neurons
get_resolution_from_dataset 3 other papers
3 later
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
2303.13995 (2023-03)
LINe: Out-of-Distribution Detection by Leveraging Important Neurons
setup_logger 2 other papers
2 later
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision

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 growing number of action classes has posed a new challenge for video understanding, making Zero-Shot Action Recognition (ZSAR) a thriving direction. The ZSAR task aims to recognize target (unseen) actions without training examples by leveraging semantic representations to bridge seen and unseen actions. However, due to the complexity and diversity of actions, it remains challenging to semantically represent action classes and transfer knowledge from seen data. In this work, we propose an ERenhanced ZSAR model inspired by an effective human memory technique Elaborative Rehearsal (ER), which involves elaborating a new concept and relating it to known concepts. Specifically, we expand each action class as an Elaborative Description (ED) sentence, which is more discriminative than a class name and less costly than manualdefined attributes. Besides directly aligning class semantics with videos, we incorporate objects from the video as Elaborative Concepts (EC) to improve video semantics and generalization from seen actions to unseen actions. Our ER-enhanced ZSAR model achieves state-of-the-art results on three existing benchmarks. Moreover, we propose a new ZSAR evaluation protocol on the Kinetics dataset to overcome limitations of current benchmarks and first compare with few-shot learning baselines on this more realistic setting. Our codes and collected EDs are released at https://github.com/DeLightCMU/ElaborativeRehearsal.

For agents

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

get_harvested_code_for_paper("2108.02833")
get_code_for_paper("2108.02833")
have("2108.02833")

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

curl https://syntology.ai/api/ran/2108.02833.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.02833.svg)](https://syntology.ai/paper/2108.02833)

Connect an agent — have() is free.