SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11148 · ICLR · 2024

Knowledge Distillation Based on Transformed Teacher Matching

En-Hui Yang, Kaixiang Zheng

arXiv · PDF · Open in the Atlas

Code that ran

5 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 0 have no contract verdict; 5 failures of our instrument; 2 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/2402.11148.json · badge: /api/ran/2402.11148.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
zkxufo/TTM canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
zkxufo/TTM/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
zkxufo/TTM/models/mobilenetv2.py
code served (permissive licence) · get_code("7765583b9e540679")
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 conv_1x1_bn takes two parameters:
# - inp: number of input channels
# - oup: number of output channels
# Both are integers representing channel dimensions

ARGS = {
    "inp": 4,
    "oup": 3,
}
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
conv_bn Ran
ran; our contract draft was wrong, not the code
zkxufo/TTM/models/mobilenetv2.py
code served (permissive licence) · get_code("2f7853ff01cbbc29")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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

torch.manual_seed(0)

inp = 3
oup = 8
stride = 2

ARGS = {
    'inp': inp,
    'oup': oup,
    'stride': stride
}
Setup block drafted by
a language model, Claude Sonnet 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 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
get_teacher_name Ran
ran; our contract draft was wrong, not the code
zkxufo/TTM/train_student.py
code served (permissive licence) · get_code("4b4f0463521302e8")
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 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 torch.nn as nn

# The function parses a model_path string to extract a teacher name
# It splits by '/' to get the second-to-last segment, then splits by '_'
# For 'wrn' models, it concatenates the first three segments
# For other models, it returns just the first segment

# We need to provide a model_path string that will be parsed correctly
model_path = "path/to/resnet_50_checkpoint/model.pt"

ARGS = {
    "model_path": model_path
}
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 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
mobilenetv2_T_w Ran
ran; our contract draft was wrong, not the code
zkxufo/TTM/models/mobilenetv2.py
code served (permissive licence) · get_code("421fd14c036bc279")
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 MobileNetV2. 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 math

torch.manual_seed(0)

ARGS = {
    'T': 6,
    'W': 1.0,
    'feature_dim': 100,
}
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 MobileNetV2 — a MobileNetV2 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNetV2 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_cifar100_dataloaders Not yet run
unverified (harvested, no recorded run)
zkxufo/TTM/dataset/cifar100.py
code served (permissive licence) · get_code("1928ecb540438f4e")
How it ran

no invocation recorded.

get_cifar100_dataloaders_sample Not yet run
unverified (harvested, no recorded run)
zkxufo/TTM/dataset/cifar100.py
code served (permissive licence) · get_code("1a2603da723a67e9")
How it ran

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, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 2 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
553 dated earlier, 8 the same month, 108 later, 17 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
conv_bn 16 other papers
15 dated earlier, 1 same year, order not determinable
1704.04861 (2017-04)
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.05049 (2019-04)
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
and 13 more not named here
conv_1x1_bn 9 other papers
9 dated earlier
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2106.04570 (2021-06)
BERT Learns to Teach: Knowledge Distillation with Meta Learning
2106.07849 (2021-06)
Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation
and 6 more not named here
get_teacher_name 6 other papers
5 dated earlier, 1 later
1910.10699 (2019-10)
Contrastive Representation Distillation
2011.01424 (2020-11)
Distilling Knowledge by Mimicking Features
2106.04570 (2021-06)
BERT Learns to Teach: Knowledge Distillation with Meta Learning
and 3 more not named here
mobilenetv2_T_w 6 other papers
6 dated earlier
2106.04570 (2021-06)
BERT Learns to Teach: Knowledge Distillation with Meta Learning
2106.07849 (2021-06)
Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation
2112.07133 (2021-12)
CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision
and 3 more not named here
get_cifar100_dataloaders 1 other paper
1 dated earlier
2305.13803 (2023-05)
NORM: Knowledge Distillation via N-to-One Representation Matching
get_cifar100_dataloaders_sample 1 other paper
1 dated earlier
2305.13803 (2023-05)
NORM: Knowledge Distillation via N-to-One Representation Matching

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

As a technique to bridge logit matching and probability distribution matching, temperature scaling plays a pivotal role in knowledge distillation (KD). Conventionally, temperature scaling is applied to both teacher's logits and student's logits in KD. Motivated by some recent works, in this paper, we drop instead temperature scaling on the student side, and systematically study the resulting variant of KD, dubbed transformed teacher matching (TTM). By reinterpreting temperature scaling as a power transform of probability distribution, we show that in comparison with the original KD, TTM has an inherent Rényi entropy term in its objective function, which serves as an extra regularization term. Extensive experiment results demonstrate that thanks to this inherent regularization, TTM leads to trained students with better generalization than the original KD. To further enhance student's capability to match teacher's power transformed probability distribution, we introduce a sample-adaptive weighting coefficient into TTM, yielding a novel distillation approach dubbed weighted TTM (WTTM). It is shown, by comprehensive experiments, that although WTTM is simple, it is effective, improves upon TTM, and achieves state-of-the-art accuracy performance. Our source code is available at https://github.com/zkxufo/TTM.

For agents

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

get_harvested_code_for_paper("2402.11148")
get_code_for_paper("2402.11148")
have("2402.11148")

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

curl https://syntology.ai/api/ran/2402.11148.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11148.svg)](https://syntology.ai/paper/2402.11148)

Connect an agent — have() is free.