SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.09536 · ACL · 2023

RIVETER Measuring Power and Social Dynamics Between Entities

Maarten Sap, Anjalie Field, Jimin Mun, Melanie Walsh, Maria Antoniak, Lauren Klein

arXiv · PDF · Open in the Atlas

Code that ran

12 of 17 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 0 have no contract verdict; 11 failures of our instrument; 5 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/2312.09536.json · badge: /api/ran/2312.09536.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
huggingface/neuralcoref canonical (classifier label)
classifier basis: census
12 ran · 5 no recorded run
FunctionStatusWhere it lives
bytes_to_unicode Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/train/compat.py
code served (permissive licence) · get_code("9e8c17dcee7cd5e4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# The function bytes_to_unicode takes a bytes object and decodes it
# Parameters:
# - b: bytes object to decode
# - encoding: string specifying the encoding (default 'utf8')
# - errors: string specifying error handling (default 'strict')

ARGS = {
    'b': b'Hello, World!',
    'encoding': 'utf8',
    'errors': 'strict'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
clean_token Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/train/conllparser.py
code served (permissive licence) · get_code("8e66fd489ce5989b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

# The function clean_token takes a single parameter: token (a string)
# It processes the token using the global NORMALIZE_DICT and REMOVED_CHAR

ARGS = {
    'token': 'test/token%example*'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
clipped_sigmoid Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/train/learn.py
code served (permissive licence) · get_code("a2124836d3557ce1")
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, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor to pass as inputs
inputs = torch.randn(2, 4)

ARGS = {
    "inputs": inputs
}
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, 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
encode_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
huggingface/neuralcoref/neuralcoref/train/utils.py
code served (permissive licence) · get_code("10347dfdc30039ba")
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, 11) 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

ARGS = {
    'x': np.array([10, 25, 50, 63], dtype=np.int64)
}
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 (4, 11) — shape (4, 11) 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
filename_to_url Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/file_utils.py
code served (permissive licence) · get_code("f45e82ab123a5616")
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 json
import os
import tempfile
from pathlib import Path

# Create a temporary directory to serve as cache
temp_cache_dir = tempfile.mkdtemp()

# Create a test filename and its associated metadata
test_filename = "test_model.bin"
cache_path = os.path.join(temp_cache_dir, test_filename)
meta_path = cache_path + ".json"

# Create dummy files with metadata
Path(cache_path).touch()

metadata = {
    "url": "https://example.com/model.bin",
    "etag": "abc123def456"
}

with open(meta_path, 'w', encoding='utf-8') as f:
    json.dump(metadata, f)

ARGS = {
    "filename": test_filename,
    "cache_dir": temp_cache_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 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_all_pairs_loss Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/train/learn.py
code served (permissive licence) · get_code("d257ae6d30634cbd")
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

torch.manual_seed(0)

# The function get_all_pairs_loss takes parameter n
# It returns all_pair_loss which takes (scores, targets)
# targets[0] is labels
# targets[4] is weights (optional, only if len(targets) == 5)
# scores and labels are used with nn.BCEWithLogitsLoss

# Create small tensors
batch_size = 2
num_classes = 4

scores = torch.randn(batch_size, num_classes)
labels = torch.randint(0, 2, (batch_size, num_classes)).float()
weights = torch.ones(batch_size, num_classes)

# targets is a tuple/list where:
# targets[0] = labels
# targets[4] = weights (if len(targets) == 5)
targets = (labels, None, None, None, weights)

n = 2

ARGS = {
    "n": n
}
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 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
hash_changed Ran
ran, violated the contract we drafted
huggingface/neuralcoref/bin/cythonize.py
code served (permissive licence) · get_code("845d81774101e9b1")
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 bool, 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 os
import hashlib
import tempfile

# Create a temporary directory and files for testing
temp_dir = tempfile.mkdtemp()
base_path = temp_dir

# Create a test file with known content
test_file_path = os.path.join(base_path, "test_file.txt")
with open(test_file_path, 'w') as f:
    f.write("test content")

# Calculate the hash of the test file
test_file_hash = hashlib.md5(open(test_file_path, 'rb').read()).hexdigest()

# Create a mock database dict
db = {
    os.path.normpath(os.path.join(base_path, "test_file.txt")): test_file_hash
}

ARGS = {
    "base": base_path,
    "path": "test_file.txt",
    "db": db
}
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 bool, 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
load_embeddings_from_file Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/train/dataset.py
code served (permissive licence) · get_code("77efc3889d645cc4")
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
import numpy as np
import tempfile
import os

# Create temporary directory and files needed by load_embeddings_from_file
temp_dir = tempfile.mkdtemp()

# Create embeddings file
embed_data = np.random.randn(10, 4).astype(np.float32)
name = os.path.join(temp_dir, 'test')
np.save(name + '_embeddings.npy', embed_data)

# Create vocabulary file
vocab_words = ['word1', 'word2', 'word3', 'word4', 'word5', 'word6', 'word7', 'word8', 'word9', 'word10']
with open(name + '_vocabulary.txt', 'w', encoding='utf-8') as f:
    for word in vocab_words:
        f.write(word + '\n')

ARGS = {
    'name': name
}
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 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
load_hashes Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/bin/cythonize.py
code served (permissive licence) · get_code("bd784b50f862d66b")
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 json
import tempfile
import os

# Create a temporary JSON file with some valid data
temp_dir = tempfile.mkdtemp()
valid_json_file = os.path.join(temp_dir, "hashes.json")
with open(valid_json_file, 'w') as f:
    json.dump({"hash1": "value1", "hash2": "value2"}, f)

ARGS = {
    "filename": valid_json_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 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
parallel_process Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
huggingface/neuralcoref/neuralcoref/train/utils.py
code served (permissive licence) · get_code("064577f26f876bc6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from time import sleep

torch.manual_seed(0)

def simple_function(x):
    """A simple function that processes a single item."""
    sleep(0.01)  # Simulate some work
    return x * 2

def dict_function(a, b):
    """A function that takes keyword arguments."""
    sleep(0.01)
    return a + b

# Test case 1: Simple array with scalar function
array_simple = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

# Test case 2: Array of dictionaries for kwargs version
array_kwargs = [
    {'a': 10, 'b': 20},
    {'a': 30, 'b': 40},
    {'a': 50, 'b': 60},
    {'a': 70, 'b': 80},
    {'a': 90, 'b': 100},
]

ARGS = {
    'array': array_simple,
    'function': simple_function,
    'n_jobs': 4,
    'use_kwargs': False,
    'front_num': 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
unicode_to_bytes Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/train/compat.py
code served (permissive licence) · get_code("ad6f3fc551889356")
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 bytes. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# unicode_to_bytes encodes a unicode string to bytes
# Parameters:
# - s: a unicode string to encode
# - encoding: the encoding format (default 'utf8')
# - errors: how to handle encoding errors (default 'strict')

ARGS = {
    's': 'Hello, World! 你好',
    'encoding': 'utf8',
    'errors': 'strict'
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
url_to_filename Ran
ran; our contract draft was wrong, not the code
huggingface/neuralcoref/neuralcoref/file_utils.py
code served (permissive licence) · get_code("5eff22fa0a651276")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from hashlib import sha256

ARGS = {
    "url": "https://example.com/model/checkpoint.bin",
    "etag": "abc123def456"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
cached_path Not yet run
unverified (harvested, no recorded run)
huggingface/neuralcoref/neuralcoref/file_utils.py
code served (permissive licence) · get_code("4cc18d5e92c311ba")
How it ran

no invocation recorded.

get_hash Not yet run
unverified (harvested, no recorded run)
huggingface/neuralcoref/bin/cythonize.py
code served (permissive licence) · get_code("7dcd71dbff03a3a0")
How it ran

no invocation recorded.

get_top_pair_loss Not yet run
unverified (harvested, no recorded run)
huggingface/neuralcoref/neuralcoref/train/learn.py
code served (permissive licence) · get_code("b04110cfd23c8567")
How it ran

no invocation recorded.

load_file Not yet run
unverified (harvested, no recorded run)
huggingface/neuralcoref/neuralcoref/train/conllparser.py
code served (permissive licence) · get_code("a7604c292d6409a3")
How it ran

no invocation recorded.

padder_collate Not yet run
unverified (harvested, no recorded run)
huggingface/neuralcoref/neuralcoref/train/dataset.py
code served (permissive licence) · get_code("3152525689191178")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 16 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
url_to_filename 48 other papers
42 dated earlier, 6 later · 8 only as an assembly brick
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 45 more not named here

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

RIVETER provides a complete easy-to-use pipeline for analyzing verb connotations associated with entities in text corpora. We prepopulate the package with connotation frames of sentiment, power, and agency, which have demonstrated usefulness for capturing social phenomena, such as gender bias, in a broad range of corpora. For decades, lexical frameworks have been foundational tools in computational social science, digital humanities, and natural language processing, facilitating multifaceted analysis of text corpora. But working with verb-centric lexica specifically requires natural language processing skills, reducing their accessibility to other researchers. By organizing the language processing pipeline, providing complete lexicon scores and visualizations for all entities in a corpus, and providing functionality for users to target specific research questions, RIVETER greatly improves the accessibility of verb lexica and can facilitate a broad range of future research.

For agents

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

get_harvested_code_for_paper("2312.09536")
get_code_for_paper("2312.09536")
have("2312.09536")

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

curl https://syntology.ai/api/ran/2312.09536.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.09536.svg)](https://syntology.ai/paper/2312.09536)

Connect an agent — have() is free.