SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.04021 · 2023

A Study on the Calibration of In-context Learning

arXiv · PDF · Open in the Atlas

Code that ran

9 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 8 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/2312.04021.json · badge: /api/ran/2312.04021.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
hlzhang109/icl-calibration canonical (classifier label)
classifier basis: census
9 ran · 8 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlzhang109/icl-calibration/llama/modeling_llama.py
code served (permissive licence) · get_code("9b4dff79d5e6102c")
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 tuple, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyze the function to understand tensor shapes:
# q, k: used in element-wise operations with cos, sin
# cos, sin: gathered using position_ids, shape [batch, heads, seq_len, dim]
# position_ids: shape [batch, seq_len], used to gather from cos/sin at dim 2

batch_size = 2
num_heads = 3
seq_len = 4
head_dim = 4

# q and k: [batch, heads, seq_len, head_dim]
q = torch.randn(batch_size, num_heads, seq_len, head_dim)
k = torch.randn(batch_size, num_heads, seq_len, head_dim)

# cos and sin: [1, heads, seq_len, head_dim] (will be repeated to batch_size)
cos = torch.randn(1, num_heads, seq_len, head_dim)
sin = torch.randn(1, num_heads, seq_len, head_dim)

# position_ids: [batch, seq_len] with values in range [0, seq_len)
position_ids = torch.tensor([
    [0, 1, 2, 3],
    [0, 1, 2, 3]
], dtype=torch.long)

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
}
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 tuple, ndim 5, 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
chunk_size_helper Ran
ran, honoured the contract we drafted
hlzhang109/icl-calibration/utils.py
code served (permissive licence) · get_code("5d4d57fcfbf81571")
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 int, ndim 0, dtype family int, 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

torch.manual_seed(0)

# Test case 1: bs is None with gpt2 model
ARGS = {
    'params': {
        'bs': None,
        'model': 'gpt2',
    }
}
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 int, ndim 0, dtype family int, 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
cross_entropy_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlzhang109/icl-calibration/calibrate/verified_calibration.py
code served (permissive licence) · get_code("19422cfbfee41729")
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 float32, 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 numpy as np

# Construct arguments for cross_entropy_loss
# The function expects:
# - logits: array of shape (batch_size, num_classes) with raw scores
# - labels: array of shape (batch_size,) with integer class indices

batch_size = 2
num_classes = 4

# Create logits: random values for each sample and class
logits = np.random.randn(batch_size, num_classes).astype(np.float32)

# Create labels: integer class indices in range [0, num_classes)
labels = np.array([0, 2], dtype=np.int32)

ARGS = {
    "logits": logits,
    "labels": labels,
}
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 float32, 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_equal_bins Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlzhang109/icl-calibration/calibration/utils.py
code served (permissive licence) · get_code("7dc9736cdb2847c4")
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 numpy as np
from typing import List

def split(sequence: List, parts: int) -> List[List]:
    assert parts <= len(sequence)
    array_splits = np.array_split(sequence, parts)
    splits = [list(l) for l in array_splits]
    assert len(splits) == parts
    return splits

def get_equal_bins(probs: List[float], num_bins: int=10) -> List[float]:
    """Get bins that contain approximately an equal number of data points."""
    sorted_probs = sorted(probs)
    if num_bins > len(sorted_probs):
        num_bins = len(sorted_probs)
    binned_data = split(sorted_probs, num_bins)
    bins: List[float] = []
    for i in range(len(binned_data) - 1):
        last_prob = binned_data[i][-1]
        next_first_prob = binned_data[i + 1][0]
        bins.append((last_prob + next_first_prob) / 2.0)
    bins.append(1.0)
    bins = sorted(list(set(bins)))
    return bins

# Create test arguments
probs_list = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99, 1.0]
num_bins_value = 5

ARGS = {
    "probs": probs_list,
    "num_bins": num_bins_value
}
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 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
get_equal_prob_bins Ran
ran; our contract draft was wrong, not the code
hlzhang109/icl-calibration/calibration/utils.py
code served (permissive licence) · get_code("d1ebc0d7093a4203")
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 torch
import numpy as np
from typing import List

torch.manual_seed(0)

# Construct arguments for get_equal_prob_bins
probs = [0.1, 0.2, 0.3, 0.4]
num_bins = 10

ARGS = {
    "probs": probs,
    "num_bins": num_bins
}
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 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
random_sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlzhang109/icl-calibration/utils.py
code served (permissive licence) · get_code("2ed507c8c59739f5")
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 2, 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 numpy as np
from copy import deepcopy

np.random.seed(0)

# Create sample sentences - list of strings
sentences = [
    "This is the first sentence.",
    "This is the second sentence.",
    "This is the third sentence.",
    "This is the fourth sentence.",
    "This is the fifth sentence.",
]

# Create sample labels - list of integers
labels = [0, 1, 0, 1, 0]

# Number of samples to randomly select
num = 3

ARGS = {
    "sentences": sentences,
    "labels": labels,
    "num": num,
}
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, ndim 2, 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
rotate_half Ran
ran; our contract draft was wrong, not the code
hlzhang109/icl-calibration/llama/modeling_llama.py
code served (permissive licence) · get_code("b99eea6376d1e212")
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

torch.manual_seed(0)

# The function rotate_half takes a single parameter 'x' which is a tensor
# It accesses x.shape[-1] to get the last dimension
# It uses indexing with [..., :] slicing notation
# It calls torch.cat() to concatenate tensors

# Create a small tensor with shape (2, 4) - batch size 2, hidden dim 4
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
setup_llama Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlzhang109/icl-calibration/utils.py
code served (permissive licence) · get_code("182e1f46c31a2e09")
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.nn as nn

torch.manual_seed(0)

# Mock the llama module since we can't download it
class MockLlamaTokenizer:
    def __init__(self):
        self.use_fast = False
        self.padding_side = 'left'
        self.pad_token = '<pad>'
        self.eos_token = '</s>'
        self.pad_token_id = 0
    
    @classmethod
    def from_pretrained(cls, model_name, use_fast=False, padding_side='left'):
        return cls()

class MockLlamaConfig:
    def __init__(self):
        self.eos_token_id = 0

class MockLlamaForCausalLM(nn.Module):
    def __init__(self, model_name):
        super().__init__()
        self.config = MockLlamaConfig()
        self.model = nn.Linear(4, 4)
    
    @classmethod
    def from_pretrained(cls, model_name, low_cpu_mem_usage=True, torch_dtype=None):
        return cls(model_name)

# Mock tensor_parallel module
class MockTensorParallel:
    @staticmethod
    def tensor_parallel(model, devices):
        return model

# Patch the imports
import sys
sys.modules['llama'] = type(sys)('llama')
sys.modules['llama'].LlamaTokenizer = MockLlamaTokenizer
sys.modules['tensor_parallel'] = type(sys)('tensor_parallel')
sys.modules['tensor_parallel'].tensor_parallel = MockTensorParallel.tensor_parallel

# Patch transformers imports
import types
transformers_module = types.ModuleType('transformers')
transformers_module.LlamaTokenizer = MockLlamaTokenizer
transformers_module.LlamaForCausalLM = MockLlamaForCausalLM
sys.modules['transformers'] = transformers_module

ARGS = {
    'model_name': 'meta-llama/Llama-2-7b',
    'half': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
llama, tensor_parallel, torch, transformers — 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
split Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlzhang109/icl-calibration/calibration/utils.py
code served (permissive licence) · get_code("8e9dfd4ba4bf9fa3")
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. 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
from typing import List, TypeVar

T = TypeVar('T')

# Set seed for reproducibility
torch.manual_seed(0)
np.random.seed(0)

# The function takes a sequence (List[T]) and an integer parts
# It uses np.array_split to split the sequence into parts
# The sequence can be any list-like object

# Create a simple test sequence
test_sequence = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
num_parts = 3

ARGS = {
    "sequence": test_sequence,
    "parts": num_parts
}
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 list — a list 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
construct_prompt Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/run_classification_cot.py
code served (permissive licence) · get_code("ef2f02ab0c2e6b74")
How it ran

no invocation recorded.

eval_accuracy Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/run_classification.py
code served (permissive licence) · get_code("556aa6b923228885")
How it ran

no invocation recorded.

get_p_content_free Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/run_classification_calibrate.py
code served (permissive licence) · get_code("d09226e56c2085ea")
How it ran

no invocation recorded.

load_commonsense_qa Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/data_utils.py
code served (permissive licence) · get_code("5459a3ffb7e8ae5f")
How it ran

no invocation recorded.

load_cot_data Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/data_utils.py
code served (permissive licence) · get_code("37240d47eb548267")
How it ran

no invocation recorded.

load_strategy_qa Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/data_utils.py
code served (permissive licence) · get_code("b74b229b1c013bd2")
How it ran

no invocation recorded.

save_pickle_tmp Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/run_classification.py
code served (permissive licence) · get_code("ac63a1554effbb56")
How it ran

no invocation recorded.

save_pickle_tmp Not yet run
unverified (harvested, no recorded run)
hlzhang109/icl-calibration/run_classification_cot.py
code served (permissive licence) · get_code("94ba60d7c3f5ef45")
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 16 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 5 later) and 10 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_half 360 other papers
47 dated earlier, 10 the same month, 300 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
apply_rotary_pos_emb 47 other papers
22 dated earlier, 2 the same month, 23 later
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
2305.16355 (2023-05)
PandaGPT: One Model To Instruction-Follow Them All
and 44 more not named here
get_equal_bins 2 other papers
1 dated earlier, 1 later
1910.12656 (2019-10)
Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
2410.10414 (2024-10)
On Calibration of LLM-based Guard Models for Reliable Content Moderation
get_equal_prob_bins 2 other papers
1 dated earlier, 1 later
1910.12656 (2019-10)
Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
2410.10414 (2024-10)
On Calibration of LLM-based Guard Models for Reliable Content Moderation
get_p_content_free 2 other papers
2 dated earlier
2005.14165 (2020-05)
Language Models are Few-Shot Learners
2102.09690 (2021-02)
Calibrate Before Use: Improving Few-Shot Performance of Language Models
split 2 other papers
1 dated earlier, 1 later
1910.12656 (2019-10)
Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
2410.10414 (2024-10)
On Calibration of LLM-based Guard Models for Reliable Content Moderation

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

Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context learning (ICL), a prevalent method for adapting static LMs through tailored prompts, and examine the balance between performance and calibration across a broad spectrum of natural language understanding and reasoning tasks. Through comprehensive experiments, we observe that, with an increasing number of ICL examples, models initially exhibit increased miscalibration before achieving better calibration and miscalibration tends to arise in low-shot settings. Moreover, we find that methods aimed at improving usability, such as fine-tuning and chain-of-thought (CoT) prompting, can lead to miscalibration and unreliable natural language explanations. Furthermore, we explore recalibration techniques and find that a scaling-binning calibrator can reduce calibration errors consistently.

For agents

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

get_harvested_code_for_paper("2312.04021")
get_code_for_paper("2312.04021")
have("2312.04021")

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

curl https://syntology.ai/api/ran/2312.04021.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.04021.svg)](https://syntology.ai/paper/2312.04021)

Connect an agent — have() is free.