SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.08153 · 2019

Learned Step Size Quantization

arXiv · PDF · Open in the Atlas

Code that ran

14 of 23 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; 4 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 3 failures of our instrument; 9 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/1902.08153.json · badge: /api/ran/1902.08153.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
zhutmost/lsq-net community (classifier label)
classifier basis not recorded on the link
9 ran · 8 no recorded run
jiyoonkm/columnquant extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
hustzxd/LSQuantization reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
ZouJiu1/LSQplus reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
zhutmost/lsq-net/model/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
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 Conv2d. 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 conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
zhutmost/lsq-net/model/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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 Conv2d. 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 = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
decompose_weights Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiyoonkm/columnquant/LSQ.py
pointer only (licence: NONE) · get_code("19f65b05591a698b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiyoonkm/columnquant 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.

get_config Ran
ran on a synthesized input
zhutmost/lsq-net/util/config.py
code served (permissive licence) · get_code("d0100ae80d1bfe92")
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 Munch. 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 argparse
import os
import munch
import yaml
import tempfile

# Create temporary YAML files for testing
temp_dir = tempfile.mkdtemp()

# Create a default configuration file
default_config = {
    'model': 'resnet18',
    'learning_rate': 0.001,
    'batch_size': 32,
    'nested': {
        'param1': 'value1',
        'param2': 42
    }
}

default_file_path = os.path.join(temp_dir, 'default_config.yaml')
with open(default_file_path, 'w') as f:
    yaml.dump(default_config, f)

# Create a custom configuration file to merge
custom_config = {
    'learning_rate': 0.01,
    'nested': {
        'param2': 100
    },
    'new_param': 'new_value'
}

custom_file_path = os.path.join(temp_dir, 'custom_config.yaml')
with open(custom_file_path, 'w') as f:
    yaml.dump(custom_config, f)

# Mock sys.argv to simulate command line arguments
import sys
original_argv = sys.argv
sys.argv = ['test_script', custom_file_path]

ARGS = {
    'default_file': default_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
munch, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Munch — a Munch output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Munch 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
grad_scale Ran
ran, honoured the contract we drafted
jiyoonkm/columnquant/LSQ.py
pointer only (licence: NONE) · get_code("a488bae52f1bfd5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiyoonkm/columnquant 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.

grad_scale Ran
ran, honoured the contract we drafted
hustzxd/LSQuantization/lsq.py
pointer only (licence: NONE) · get_code("d75564df9359ef7b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hustzxd/LSQuantization 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.

init_logger Ran
ran on a synthesized input
zhutmost/lsq-net/util/config.py
code served (permissive licence) · get_code("dcafab1705c6104a")
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 PosixPath. 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 time
from pathlib import Path
import tempfile

# Create a temporary directory for the output
temp_dir = tempfile.TemporaryDirectory()
output_dir = Path(temp_dir.name)

# Create a minimal logging config file
cfg_file = output_dir / "logging.cfg"
cfg_file.write_text("""[loggers]
keys=root

[handlers]
keys=fileHandler

[formatters]
keys=standard

[logger_root]
level=DEBUG
handlers=fileHandler

[handler_fileHandler]
class=FileHandler
level=DEBUG
formatter=standard
args=('%(logfilename)s',)

[formatter_standard]
format=%(asctime)s - %(name)s - %(levelname)s - %(message)s
""")

ARGS = {
    'experiment_name': 'test_experiment',
    'output_dir': output_dir,
    'cfg_file': str(cfg_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 PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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
lr_scheduler Ran
ran on a synthesized input
zhutmost/lsq-net/util/lr_scheduler.py
code served (permissive licence) · get_code("39de768061885cd0")
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 CosineLr. 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)

# Create a minimal model
model = nn.Linear(4, 3)

# Create an optimizer with param_groups
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Define all parameters for lr_scheduler function
ARGS = {
    'optimizer': optimizer,
    'mode': 'cos',
    'batch_size': 32,
    'num_samples': 1000,
    'update_per_batch': False,
    'lr_min': 0.0,
    'cycle': 90
}
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 CosineLr — a CosineLr output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CosineLr 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
merge_nested_dict Ran
ran on a synthesized input
zhutmost/lsq-net/util/config.py
code served (permissive licence) · get_code("742d60dfe2ec0c9f")
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 numpy as np

torch.manual_seed(0)

# Construct arguments for merge_nested_dict
# The function takes two dictionaries and merges them recursively

# Create first dictionary with nested structure
d = {
    "model_config": {
        "hidden_size": 256,
        "num_layers": 3,
        "dropout": 0.1
    },
    "training": {
        "learning_rate": 0.001,
        "batch_size": 32
    },
    "name": "baseline"
}

# Create second dictionary with some overlapping and new keys
other = {
    "model_config": {
        "hidden_size": 512,
        "activation": "relu"
    },
    "training": {
        "epochs": 100
    },
    "seed": 42
}

ARGS = {
    "d": d,
    "other": other
}
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 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
resnet20 Ran
ran on a synthesized input
zhutmost/lsq-net/model/resnet_cifar.py
code served (permissive licence) · get_code("d759ea54f50325b0")
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 ResNet. 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 = {
    'pretrained': False,
    'progress': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet32 Ran
ran on a synthesized input
zhutmost/lsq-net/model/resnet_cifar.py
code served (permissive licence) · get_code("472d3c550a61f926")
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 ResNet. 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 = {
    'pretrained': False,
    'progress': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet44 Ran
ran on a synthesized input
zhutmost/lsq-net/model/resnet_cifar.py
code served (permissive licence) · get_code("1db27ae5efae49cc")
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 ResNet. 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 = {
    'pretrained': False,
    'progress': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
round_pass Ran
ran, honoured the contract we drafted
jiyoonkm/columnquant/LSQ.py
pointer only (licence: NONE) · get_code("ed1a69e092272dba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiyoonkm/columnquant 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.

round_pass Ran
ran, honoured the contract we drafted
hustzxd/LSQuantization/lsq.py
pointer only (licence: NONE) · get_code("40027e5e78ca8837")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hustzxd/LSQuantization 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.

accuracy Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/process.py
code served (permissive licence) · get_code("9453c291b0f1f0bc")
How it ran

no invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/model/model.py
code served (permissive licence) · get_code("cfdac0ab4bbef047")
How it ran

no invocation recorded.

find_modules_to_quantize Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/quan/utils.py
code served (permissive licence) · get_code("d111297ab7138f2f")
How it ran

no invocation recorded.

load_checkpoint Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/util/checkpoint.py
code served (permissive licence) · get_code("ecf0e2f2f2b1b80a")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/util/data_loader.py
code served (permissive licence) · get_code("72f8eaea5e7a643d")
How it ran

no invocation recorded.

prepare Not yet run
unverified (harvested, no recorded run)
ZouJiu1/LSQplus/quantization/lsqquantize_V1.py
pointer only (licence: GPL-3.0) · get_code("bd2c949ff15695e5")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, ZouJiu1/LSQplus, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

quantizer Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/quan/utils.py
code served (permissive licence) · get_code("c5c793591e0a89c4")
How it ran

no invocation recorded.

replace_module_by_names Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/quan/utils.py
code served (permissive licence) · get_code("cd4da274de64134b")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
zhutmost/lsq-net/model/resnet.py
code served (permissive licence) · get_code("3f5510bd7f92fad4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 7 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
conv1x1 431 other papers
22 dated earlier, 1 the same month, 407 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
9 dated earlier, 302 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
1 dated earlier, 93 later, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
1911.06487 (2019-11)
OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning
and 92 more not named here
grad_scale 5 other papers
5 later
2201.07703 (2022-01)
Q-ViT: Fully Differentiable Quantization for Vision Transformer
aaai_28109 (2024 (year only))
Bi-ViT: Pushing the Limit of Vision Transformer Quantization
2404.05662 (2024-04)
BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
and 2 more not named here
round_pass 5 other papers
5 later
2201.07703 (2022-01)
Q-ViT: Fully Differentiable Quantization for Vision Transformer
aaai_28109 (2024 (year only))
Bi-ViT: Pushing the Limit of Vision Transformer Quantization
2404.05662 (2024-04)
BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
and 2 more not named here
grad_scale 4 other papers
4 later
2004.09576 (2020-04)
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
2203.08368 (2022-03)
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
2302.02210 (2023-02)
Oscillation-free Quantization for Low-bit Vision Transformers
and 1 more not named here
round_pass 4 other papers
4 later
2004.09576 (2020-04)
LSQ+: Improving low-bit quantization through learnable offsets and better initialization
2203.08368 (2022-03)
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
2302.02210 (2023-02)
Oscillation-free Quantization for Low-bit Vision Transformers
and 1 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

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a method for training such networks, Learned Step Size Quantization, that achieves the highest accuracy to date on the ImageNet dataset when using models, from a variety of architectures, with weights and activations quantized to 2-, 3- or 4-bits of precision, and that can train 3-bit models that reach full precision baseline accuracy. Our approach builds upon existing methods for learning weights in quantized networks by improving how the quantizer itself is configured. Specifically, we introduce a novel means to estimate and scale the task loss gradient at each weight and activation layer's quantizer step size, such that it can be learned in conjunction with other network parameters. This approach works using different levels of precision as needed for a given system and requires only a simple modification of existing training code.

For agents

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

get_harvested_code_for_paper("1902.08153")
get_code_for_paper("1902.08153")
have("1902.08153")

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

curl https://syntology.ai/api/ran/1902.08153.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.08153.svg)](https://syntology.ai/paper/1902.08153)

Connect an agent — have() is free.