SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.12666 · ICCV · 2023

Bayesian Optimization Meets Self-Distillation

Heon Song, Hyunjae Lee, Hyeonsoo Lee, Gi-Hyeon Lee, Suyeong Donggeun, Yoo Lunit

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2304.12666.json · badge: /api/ran/2304.12666.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
sooperset/boss canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
colorize Ran
ran; our contract draft was wrong, not the code
sooperset/boss/utils/visualize.py
code served (permissive licence) · get_code("c87e7665fde6cdfc")
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 3, dtype family float, shape (3, 4, 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)

# The function colorize takes a single parameter x which should be a tensor
# Looking at the function body:
# - x can be 2D, 3D, or 4D
# - For 3D: x.size(1) and x.size(2) are used (height, width)
# - For 4D: x.size(0) is batch, x.size(2) and x.size(3) are height/width
# The function applies gaussian operations on x values, so it should contain
# grayscale image data (values roughly in [0,1] or similar range)

# Create a small 3D tensor (1 channel, 4 height, 3 width)
x_3d = torch.rand(1, 4, 3)

ARGS = {
    "x": x_3d
}
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 3, dtype family float, shape (3, 4, 3) — shape (3, 4, 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
gauss Ran
ran on a synthesized input
sooperset/boss/utils/visualize.py
code served (permissive licence) · get_code("d66f0a3cbb86204c")
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)

# The gauss function performs Gaussian operations on tensors
# Parameters x, a, b, c are all used in arithmetic operations
# They should all be tensors (or scalar-like values that torch operations can handle)

x = torch.randn(2, 4)
a = torch.randn(2, 4)
b = torch.randn(2, 4)
c = torch.randn(2, 4)

ARGS = {
    'x': x,
    'a': a,
    'b': b,
    'c': c
}
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
make_image Ran
ran on a synthesized input
sooperset/boss/utils/visualize.py
code served (permissive licence) · get_code("1394422d51c4b126")
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 3, dtype family float, shape (4, 5, 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
import numpy as np

torch.manual_seed(0)

# Create a small tensor with shape (3, 4, 5) - 3 channels, 4x5 spatial dimensions
# This tensor will be modified in-place and needs to support .numpy()
img = torch.randn(3, 4, 5)

# Define mean and std tuples
mean = (0.5, 0.3, 0.2)
std = (0.1, 0.2, 0.15)

ARGS = {
    "img": img,
    "mean": mean,
    "std": std,
}
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 ndarray, ndim 3, dtype family float, shape (4, 5, 3) — shape (4, 5, 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
make_layers Ran
ran; our contract draft was wrong, not the code
sooperset/boss/models/cifar/vgg.py
code served (permissive licence) · get_code("ac62432dc5134b0d")
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 Sequential. 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 takes two parameters: cfg and batch_norm
# cfg should be a list/sequence of either integers (channel counts) or 'M' (maxpool marker)
# batch_norm is a boolean flag

# Using one of the predefined configurations from the module-level cfg dict
cfg_list = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M']

ARGS = {
    'cfg': cfg_list,
    'batch_norm': False
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
plot_overlap Ran
ran; our contract draft was wrong, not the code
sooperset/boss/utils/logger.py
code served (permissive licence) · get_code("50afa2863ffd9fde")
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 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 matplotlib.pyplot as plt
import numpy as np

class MockLogger:
    def __init__(self):
        self.title = "TestPlot"
        self.names = ["loss", "accuracy", "f1_score"]
        self.numbers = {
            "loss": [0.5, 0.4, 0.3, 0.2],
            "accuracy": [0.7, 0.75, 0.8, 0.85],
            "f1_score": [0.65, 0.72, 0.78, 0.82]
        }

logger = MockLogger()

ARGS = {
    "logger": logger,
    "names": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
matplotlib, 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
run_trial Ran
ran on a synthesized input
sooperset/boss/cifar_boss.py
code served (permissive licence) · get_code("7fce49869492eca4")
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 Popen. 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 subprocess
import tempfile
import os

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

ARGS = {
    'gpu_id': 0,
    'seed': 42,
    'study_name': 'test_study',
    'storage_path': temp_dir,
    'arch': 'resnet18',
    'dataset': 'cifar10',
    'workers': 4,
    'is_warmup_trial': False,
    'pretrained_mode': False
}
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 Popen — a Popen output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Popen output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_mean_and_std Not yet run
unverified (harvested, no recorded run)
sooperset/boss/utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from LeeHyuck/CDMAD, is pointer only (licence: NONE) · get_code("1d6e2edb8832d7b0")
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 LeeHyuck/CDMAD, 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. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 1 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
make_layers 59 other papers
38 dated earlier, 20 later, 1 same year, order not determinable
1411.4038 (2014-11)
Fully Convolutional Networks for Semantic Segmentation
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1511.05950 (2015-11)
Staleness-aware Async-SGD for Distributed Deep Learning
and 56 more not named here
plot_overlap 31 other papers
21 dated earlier, 10 later
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
and 28 more not named here
get_mean_and_std 21 other papers
16 dated earlier, 5 later
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1811.05850 (2018-11)
Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
and 18 more not named here
colorize 11 other papers
10 dated earlier, 1 later
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1811.05850 (2018-11)
Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
and 8 more not named here
gauss 11 other papers
10 dated earlier, 1 later
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1811.05850 (2018-11)
Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
and 8 more not named here
make_image 11 other papers
10 dated earlier, 1 later
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1811.05850 (2018-11)
Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
and 8 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

Bayesian optimization (BO) has contributed greatly to improving model performance by suggesting promising hyperparameter configurations iteratively based on observations from multiple training trials. However, only partial knowledge (i.e., the measured performances of trained models and their hyperparameter configurations) from previous trials is transferred. On the other hand, Self-Distillation (SD) only transfers partial knowledge learned by the task model itself. To fully leverage the various knowledge gained from all training trials, we propose the BOSS framework, which combines BO and SD. BOSS suggests promising hyperparameter configurations through BO and carefully selects pre-trained models from previous trials for SD, which are otherwise abandoned in the conventional BO process. BOSS achieves significantly better performance than both BO and SD in a wide range of tasks including general image classification, learning with noisy labels, semi-supervised learning, and medical image analysis tasks. Our code is available at https://github.com/sooperset/boss.

For agents

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

get_harvested_code_for_paper("2304.12666")
get_code_for_paper("2304.12666")
have("2304.12666")

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

curl https://syntology.ai/api/ran/2304.12666.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.12666.svg)](https://syntology.ai/paper/2304.12666)

Connect an agent — have() is free.