SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02010 · 2023

Towards Learning a Generalist Model for Embodied Navigation

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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 7 failures of our instrument; 5 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2312.02010.json · badge: /api/ran/2312.02010.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
lavi-lab/navillm canonical (classifier label)
classifier basis: census
9 ran · 5 no recorded run
zd11024/NaviLLM canonical (classifier label)
classifier basis: plan_row
1 ran · 0 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
lavi-lab/navillm/models/vln_bert.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). 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 swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (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
build_dataloader Ran
ran on a synthesized input
lavi-lab/navillm/tasks/loaders.py
code served (permissive licence) · get_code("dd2ac0ab9c587094")
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. 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 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 torch.utils.data as data
from torch.utils.data import Dataset

torch.manual_seed(0)

# Create a minimal dataset class with collate_batch method
class DummyDataset(Dataset):
    def __init__(self, size=8):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(4), torch.randint(0, 2, (1,))
    
    def collate_batch(self, batch):
        xs = torch.stack([item[0] for item in batch])
        ys = torch.stack([item[1] for item in batch])
        return xs, ys

# Create dataset instance
dataset = DummyDataset(size=8)

ARGS = {
    "dataset": dataset,
    "distributed": False,
    "training": True,
    "batch_size": 2,
    "num_workers": 0,
}
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
calc_position_distance Ran
ran, violated the contract we drafted
lavi-lab/navillm/models/graph_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from cshizhe/vln-duet, is pointer only (licence: NONE) · get_code("c362aaed2935ceff")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cshizhe/vln-duet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_vp_rel_pos_fts Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lavi-lab/navillm/models/graph_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from cshizhe/vln-duet, is pointer only (licence: NONE) · get_code("168e35f8ed1ad0ce")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cshizhe/vln-duet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_feature_db Ran
ran; our contract draft was wrong, not the code
lavi-lab/navillm/tasks/feature_db.py
code served (permissive licence) · get_code("98a915bad0a2f94d")
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 os
import h5py
import numpy as np
import tempfile

# Create a temporary HDF5 file with test data
temp_dir = tempfile.mkdtemp()
h5_file = os.path.join(temp_dir, "test_features.h5")

with h5py.File(h5_file, 'w') as f:
    # Create some test datasets
    # 1D feature array
    f.create_dataset('scan1_view1', data=np.random.randn(128).astype(np.float32))
    # 2D feature array (multiple views)
    f.create_dataset('scan2_view2', data=np.random.randn(10, 128).astype(np.float32))
    # Another 1D array
    f.create_dataset('scan3', data=np.random.randn(256).astype(np.float32))

# Create a minimal args object with data_dir attribute
class Args:
    def __init__(self, data_dir):
        self.data_dir = data_dir

args = Args(temp_dir)

# Create config dict mapping source names to file paths
config = {
    'rgb': h5_file,
    'depth': h5_file,
}

ARGS = {
    'config': config,
    'image_feat_size': 64,
    'args': args,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — 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
extend_neg_masks Ran
ran; our contract draft was wrong, not the code
lavi-lab/navillm/models/ops.py
code served (permissive licence) · get_code("91e1742acf23aa57")
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, 1, 1, 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)

# Construct a small mask tensor of shape (N, L) with binary values
# N=2 (batch size), L=4 (sequence length)
masks = torch.randint(0, 2, (2, 4)).float()

ARGS = {
    "masks": masks,
    "dtype": torch.float,
}
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, 1, 1, 4) — shape (2, 1, 1, 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
gelu Ran
ran, honoured the contract we drafted
zd11024/NaviLLM/models/vln_bert.py
code served (permissive licence) · get_code("c2f0705ed8e6f7e6")
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 Tensor, ndim 2, dtype family float, shape (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 torch
import math

torch.manual_seed(0)

# The gelu function takes a single parameter 'x' which should be a tensor
# The function applies element-wise operations: multiplication, addition, torch.erf, and division
# So x should be a torch.Tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (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
gen_seq_masks Ran
ran; our contract draft was wrong, not the code
lavi-lab/navillm/models/ops.py
code served (permissive licence) · get_code("d9c76c6dc9976905")
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, 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)

# Create a sequence lengths tensor
# The function expects seq_lens to be a 1D tensor with batch_size elements
# It calls .device on it and .unsqueeze(1) on it
seq_lens = torch.tensor([3, 2], dtype=torch.long)  # batch_size=2, values are sequence lengths

# max_len can be None (function will compute it) or an integer
max_len = None

ARGS = {
    "seq_lens": seq_lens,
    "max_len": max_len,
}
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, 3) — shape (2, 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_angle_fts Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lavi-lab/navillm/models/graph_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from cshizhe/vln-duet, is pointer only (licence: NONE) · get_code("dac1993f5ce8e12e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cshizhe/vln-duet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

move_to_cuda Ran
ran; our contract draft was wrong, not the code
lavi-lab/navillm/tasks/loaders.py
code served (permissive licence) · get_code("a581dc0bf92d2ee5")
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
from typing import List, Dict, Tuple, Union

torch.manual_seed(0)

# Create a small tensor
tensor_arg = torch.randn(2, 4)

# Create a list batch containing tensors
list_batch = [torch.randn(2, 4), torch.randn(3, 5)]

# Create a tuple batch containing tensors
tuple_batch = (torch.randn(2, 4), torch.randn(3, 5))

# Create a dict batch containing tensors
dict_batch = {
    "input": torch.randn(2, 4),
    "target": torch.randn(2, 3),
    "metadata": torch.randn(1, 6)
}

# Create a device (CPU only)
device = torch.device("cpu")

# Define ARGS with all parameter combinations
ARGS = {
    "batch": dict_batch,
    "device": device
}
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
build_transformer Not yet run
unverified (harvested, no recorded run)
lavi-lab/navillm/models/detr_transformer.py
code served (permissive licence) · get_code("df2919fd1dad1d43")
How it ran

no invocation recorded.

create_dataloaders Not yet run
unverified (harvested, no recorded run)
lavi-lab/navillm/tasks/loaders.py
code served (permissive licence) · get_code("1a2aa37d868fb374")
How it ran

no invocation recorded.

create_transformer_encoder Not yet run
unverified (harvested, no recorded run)
lavi-lab/navillm/models/ops.py
code served (permissive licence) · get_code("bdc0b119cec4f508")
How it ran

no invocation recorded.

init_vis_config Not yet run
unverified (harvested, no recorded run)
lavi-lab/navillm/models/nav_model.py
code served (permissive licence) · get_code("7d0ae7f5c781116b")
How it ran

no invocation recorded.

llama_model_in_debug_model Not yet run
unverified (harvested, no recorded run)
lavi-lab/navillm/models/vln_bert.py
code served (permissive licence) · get_code("6288ee4b92b46305")
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, 15 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 2 the same month, 15 later) and 0 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
swish 206 other papers
167 dated earlier, 3 the same month, 36 later · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
gelu 198 other papers
160 dated earlier, 1 the same month, 36 later, 1 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
build_transformer 32 other papers
20 dated earlier, 12 later
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2104.04369 (2021-04)
Video-aided Unsupervised Grammar Induction
and 29 more not named here
calc_position_distance 8 other papers
3 dated earlier, 5 later
2202.11742 (2022-02)
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
2307.12907 (2023-07)
GridMM: Grid Memory Map for Vision-and-Language Navigation
2308.04758 (2023-08)
Bird's-Eye-View Scene Graph for Vision-Language Navigation
and 5 more not named here
extend_neg_masks 8 other papers
3 dated earlier, 5 later · 4 only as an assembly brick
2303.15796 (2023-03)
KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation
2305.03602 (2023-05)
A Dual Semantic-Aware Recurrent Global-Adaptive Network for Vision-and-Language Navigation
2308.04758 (2023-08)
Bird's-Eye-View Scene Graph for Vision-Language Navigation
and 5 more not named here
gen_seq_masks 8 other papers
3 dated earlier, 5 later · 4 only as an assembly brick
2303.15796 (2023-03)
KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation
2305.03602 (2023-05)
A Dual Semantic-Aware Recurrent Global-Adaptive Network for Vision-and-Language Navigation
2308.04758 (2023-08)
Bird's-Eye-View Scene Graph for Vision-Language Navigation
and 5 more not named here
create_transformer_encoder 7 other papers
3 dated earlier, 4 later · 2 only as an assembly brick
2303.15796 (2023-03)
KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation
2305.03602 (2023-05)
A Dual Semantic-Aware Recurrent Global-Adaptive Network for Vision-and-Language Navigation
2308.04758 (2023-08)
Bird's-Eye-View Scene Graph for Vision-Language Navigation
and 4 more not named here
get_angle_fts 7 other papers
2 dated earlier, 5 later
2202.11742 (2022-02)
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
2308.04758 (2023-08)
Bird's-Eye-View Scene Graph for Vision-Language Navigation
and 4 more not named here
calculate_vp_rel_pos_fts 6 other papers
3 dated earlier, 3 later
2202.11742 (2022-02)
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
2307.12907 (2023-07)
GridMM: Grid Memory Map for Vision-and-Language Navigation
2308.04758 (2023-08)
Bird's-Eye-View Scene Graph for Vision-Language Navigation
and 3 more not named here
build_dataloader 1 other paper
1 later
Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper (2024 (year only))
Towards Learning a Generalist Model for Embodied Navigation
create_dataloaders 1 other paper
1 later
Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper (2024 (year only))
Towards Learning a Generalist Model for Embodied Navigation
create_feature_db 1 other paper
1 later
Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper (2024 (year only))
Towards Learning a Generalist Model for Embodied Navigation
init_vis_config 1 other paper
1 later
Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper (2024 (year only))
Towards Learning a Generalist Model for Embodied Navigation
llama_model_in_debug_model 1 other paper
1 later
Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper (2024 (year only))
Towards Learning a Generalist Model for Embodied Navigation
move_to_cuda 1 other paper
1 later
Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper (2024 (year only))
Towards Learning a Generalist Model for Embodied Navigation

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

Building a generalist agent that can interact with the world is the intriguing target of AI systems, thus spurring the research for embodied navigation, where an agent is required to navigate according to instructions or respond to queries. Despite the major progress attained, previous works primarily focus on task-specific agents and lack generalizability to unseen scenarios. Recently, LLMs have presented remarkable capabilities across various fields, and provided a promising opportunity for embodied navigation. Drawing on this, we propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. The schema-based instruction flexibly casts various tasks into generation problems, thereby unifying a wide range of tasks. This approach allows us to integrate diverse data sources from various datasets into the training, equipping NaviLLM with a wide range of capabilities required by embodied navigation. We conduct extensive experiments to evaluate the performance and generalizability of our model. The experimental results demonstrate that our unified model achieves state-of-the-art performance on CVDN, SOON, and ScanQA. Specifically, it surpasses the previous stats-of-the-art method by a significant margin of 29% in goal progress on CVDN. Moreover, our model also demonstrates strong generalizability and presents impressive results on unseen tasks, e.g., embodied question answering and 3D captioning.

For agents

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

get_harvested_code_for_paper("2312.02010")
get_code_for_paper("2312.02010")
have("2312.02010")

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

curl https://syntology.ai/api/ran/2312.02010.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02010.svg)](https://syntology.ai/paper/2312.02010)

Connect an agent — have() is free.