SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 00676 · ECCV · 2024

Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search

Lujun Li, Shitong Shao, Peijie Dong, Zimian Wei, Haosen Sun

Open in the Atlas

Code that ran

3 of 6 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, 2 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 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/00676.json · badge: /api/ran/00676.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
lliai/Auto-DAS canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
calculate_md5 Ran
ran; our contract draft was wrong, not the code
lliai/Auto-DAS/autodas/datasets/imagenet16.py
code served (permissive licence) · get_code("5c3574e986df9984")
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 hashlib
import tempfile
import os

# Create a temporary file with some test content
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.bin') as f:
    temp_file_path = f.name
    f.write(b'This is test content for MD5 calculation. ' * 100)

ARGS = {
    'fpath': temp_file_path,
    'chunk_size': 1024 * 1024,
}
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
check_integrity Ran
ran, violated the contract we drafted
lliai/Auto-DAS/autodas/datasets/imagenet16.py
code served (permissive licence) · get_code("24aee327ca41fde9")
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 hashlib
import os
import tempfile

# Create a temporary file with some content
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.txt') as f:
    temp_file_path = f.name
    f.write(b'Hello, World!')

# Calculate the MD5 hash of the temporary file
md5_hash = hashlib.md5()
with open(temp_file_path, 'rb') as f:
    md5_hash.update(f.read())
correct_md5 = md5_hash.hexdigest()

# Define arguments for check_integrity
ARGS = {
    'fpath': temp_file_path,
    'md5': correct_md5
}
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
check_md5 Ran
ran, violated the contract we drafted
lliai/Auto-DAS/autodas/datasets/imagenet16.py
code served (permissive licence) · get_code("b3cb500b2f04323d")
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 tempfile
import os
import hashlib

# Create a temporary file with known content
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_file.bin")

# Write some test data to the file
test_data = b"Hello, this is test content for MD5 calculation!"
with open(temp_file, 'wb') as f:
    f.write(test_data)

# Calculate the actual MD5 hash of the test file
md5_hash = hashlib.md5()
md5_hash.update(test_data)
correct_md5 = md5_hash.hexdigest()

# Define arguments for check_md5 function
ARGS = {
    'fpath': temp_file,
    'md5': correct_md5
}
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
get_dataloader_sample Not yet run
unverified (harvested, no recorded run)
lliai/Auto-DAS/autodas/datasets/imagenet.py
code served (permissive licence) · get_code("fe05db7a8556021c")
How it ran

no invocation recorded.

get_imagenet_dataloader Not yet run
unverified (harvested, no recorded run)
lliai/Auto-DAS/autodas/datasets/imagenet.py
code served (permissive licence) · get_code("431f0c3503ec0fc0")
How it ran

no invocation recorded.

get_test_loader Not yet run
unverified (harvested, no recorded run)
lliai/Auto-DAS/autodas/datasets/imagenet.py
code served (permissive licence) · get_code("075f9564564ebd10")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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, 0 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
calculate_md5 13 other papers
11 dated earlier, 2 same year, order not determinable
2001.00326 (2020-01)
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
2003.09553 (2020-03)
Adversarial Continual Learning
2106.05390 (2021-06)
Optimizing Reusable Knowledge for Continual Learning via Metalearning
and 10 more not named here
check_md5 13 other papers
11 dated earlier, 2 same year, order not determinable
2001.00326 (2020-01)
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
2003.09553 (2020-03)
Adversarial Continual Learning
2106.05390 (2021-06)
Optimizing Reusable Knowledge for Continual Learning via Metalearning
and 10 more not named here
check_integrity 6 other papers
5 dated earlier, 1 same year, order not determinable
2001.00326 (2020-01)
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
2108.11939 (2021-08)
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
2205.05662 (2022-05)
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
and 3 more not named here
get_test_loader 3 other papers
3 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
2305.13803 (2023-05)
NORM: Knowledge Distillation via N-to-One Representation Matching
get_dataloader_sample 2 other papers
2 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
get_imagenet_dataloader 2 other papers
2 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

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

Distillation-aware Architecture Search (DAS) seeks to discover the ideal student architecture that delivers superior performance by distilling knowledge from a given teacher model. Previous DAS methods involve time-consuming training-based search processes. Recently, the training-free DAS method (i.e., DisWOT) proposes KD-based proxies and achieves significant search acceleration. However, we observe that DisWOT suffers from limitations such as the need for manual design and poor generalization to diverse architectures, such as the Vision Transformer (ViT). To address these issues, we present Auto-DAS, an automatic proxy discovery framework using an Evolutionary Algorithm (EA) for training-free DAS. Specifically, we empirically find that proxies conditioned on student instinct statistics and teacher-student interaction statistics can effectively predict distillation accuracy. Then, we represent the proxy with computation graphs and construct the proxy search space using instinct and interaction statistics as inputs. To identify promising proxies, our search space incorporates various types of basic transformations and network distance operators inspired by previous proxy and KDloss designs. Next, our EA initializes populations, evaluates, performs crossover and mutation operations, and selects the best correlation candidate with distillation accuracy. We introduce an adaptive-elite selection strategy to enhance search efficiency and strive for a balance between exploitation and exploration. Finally, we conduct training-free DAS with discovered proxy before the optimal student distillation phase. In this way, our auto-discovery framework eliminates the need for manual design and tuning, while also adapting to different search spaces through direct correlation optimization. Extensive experiments demonstrate that Auto-DAS generalizes well to various architectures and search spaces (e.g., ResNet, ViT, NAS-Bench-101, and NAS-Bench-201), achieving state-ofthe-art results in both ranking correlation and final searched accuracy. Code at: https://github.com/lliai/Auto-DAS.

For agents

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

get_harvested_code_for_paper("00676")
get_code_for_paper("00676")
have("00676")

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

curl https://syntology.ai/api/ran/00676.json

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

[![Syntology run record](https://syntology.ai/api/ran/00676.svg)](https://syntology.ai/paper/00676)

Connect an agent — have() is free.