SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.11939 · 2021

Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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 10 have no contract verdict; 1 failure of our instrument; 1 no recorded run); 2 of them were also run on the host, not in the jail, by the peer-agreement lane that set their level, 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/2108.11939.json · badge: /api/ran/2108.11939.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
vita-group/tegnas canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_md5 Ran
ran; our contract draft was wrong, not the code
vita-group/tegnas/lib/datasets/DownsampledImageNet.py
code served (permissive licence) · get_code("ad0636a128295d5a")
How it ran

Ran in Syntology's jail 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. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T01:26:15Z). 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 os
import tempfile
import hashlib

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

# Write some test data to the file
with open(test_file, 'wb') as f:
    f.write(b"Hello, this is test data for MD5 calculation." * 100)

ARGS = {
    "fpath": test_file,
    "chunk_size": 1024 * 1024
}
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
check_md5 Ran
ran, violated the contract we drafted
vita-group/tegnas/lib/datasets/DownsampledImageNet.py
code served (permissive licence) · get_code("380a00b777aad655")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:17:45Z). 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 os
import sys
import hashlib
import torch
import tempfile

# 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 data for MD5 calculation!"
with open(temp_file, 'wb') as f:
    f.write(test_data)

# Calculate the MD5 hash of the test data
md5_hash = hashlib.md5(test_data).hexdigest()

# Define arguments for check_md5 function
ARGS = {
    'fpath': temp_file,
    'md5': md5_hash
}
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 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
additive_func Ran
ran on a synthesized input
vita-group/tegnas/lib/models/SharedUtils.py
code served (permissive licence) · get_code("90b82aa39b904530")
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)

# Create two tensors with batch size 2
# Test case 1: A and B have same dimensions
A = torch.randn(2, 4)
B = torch.randn(2, 4)

ARGS = {
    "A": A,
    "B": B,
}
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
change_key Ran
ran on a synthesized input
vita-group/tegnas/lib/models/SharedUtils.py
code served (permissive licence) · get_code("11f5fc83cf977b27")
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 function. 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 change_key takes a key (string) and value (any type)
# and returns a function that sets that attribute on modules
# The returned function is typically used with module.apply()

class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.weight = torch.randn(2, 3)
        self.bias = torch.randn(4)
        self.custom_attr = "old_value"

# Create a test module
module = SimpleModule()

# Define arguments for change_key function
# key: the attribute name to change
# value: the new value to set for that attribute
key_arg = "custom_attr"
value_arg = "new_value"

ARGS = {
    "key": key_arg,
    "value": value_arg
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
vita-group/tegnas/lib/datasets/DownsampledImageNet.py
code served (permissive licence) · get_code("e947a6effcaaf32b")
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 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 os
import tempfile
import hashlib

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

# Write some test content to the file
with open(test_file, 'w') as f:
    f.write("test content for md5 checking")

# Calculate the MD5 hash of the test file
md5_hash = hashlib.md5()
with open(test_file, 'rb') as f:
    for chunk in iter(lambda: f.read(1024 * 1024), b''):
        md5_hash.update(chunk)
correct_md5 = md5_hash.hexdigest()

# Define arguments for check_integrity function
ARGS = {
    'fpath': test_file,
    'md5': correct_md5
}
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 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
convert_param Ran
ran on a synthesized input
vita-group/tegnas/lib/config_utils/configure_utils.py
code served (permissive licence) · get_code("0ab5da378bc47caa")
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 numpy as np

# Test case 1: Converting a single int
test1 = ['int', '42']

# Test case 2: Converting a list of strings
test2 = ['str', ['hello', 'world', 'test']]

# Test case 3: Converting a single bool
test3 = ['bool', '1']

# Test case 4: Converting a list of floats
test4 = ['float', ['3.14', '2.71', '1.41']]

# Test case 5: Converting a single none
test5 = ['none', 'none']

# Test case 6: Converting a list with mixed numeric strings
test6 = ['int', ['1', '2', '3', '4']]

# Test case 7: Converting a bool from '0'
test7 = ['bool', '0']

# Test case 8: Single float value
test8 = ['float', '99.99']

# Test case 9: List of strings with special characters
test9 = ['str', ['param1', 'param2', 'config_value']]

# Test case 10: None type single value
test10 = ['none', 'none']

ARGS = {
    'original_lists': test1
}
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 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
convert_secs2time Ran
ran on a synthesized input
vita-group/tegnas/lib/log_utils/time_utils.py
code served (permissive licence) · get_code("a7d5163e9c07e8a6")
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 int; 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

# Define ARGS dict with parameters for convert_secs2time
ARGS = {
    'epoch_time': 3661.5,  # 1 hour, 1 minute, 1.5 seconds
    'return_str': 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 tuple, ndim 1, dtype family int — 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
load_config_dict Ran
ran on a synthesized input
vita-group/tegnas/lib/config_utils/configure_utils.py
code served (permissive licence) · get_code("4e7d2fa9844f3b3f")
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 os
import json
import tempfile

# Create a temporary directory and a test config file
temp_dir = tempfile.mkdtemp()
config_path = os.path.join(temp_dir, 'test_config.json')

# Create a valid config file with various parameter types
config_data = {
    "learning_rate": ["float", 0.001],
    "batch_size": ["int", 32],
    "use_cuda": ["bool", 0],
    "model_name": ["str", "resnet50"],
    "epochs": ["int", [10, 20, 30]],
    "dropout": ["float", [0.1, 0.2]],
    "checkpoint": ["none", "none"]
}

with open(config_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    'path': config_path
}
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 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
merge_config_dict Ran
ran on a synthesized input
vita-group/tegnas/lib/config_utils/configure_utils.py
code served (permissive licence) · get_code("016af1fb2ba7cc2b")
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

torch.manual_seed(0)

# Construct valid arguments for merge_config_dict
# The function takes a list of dictionaries and merges them together

config1 = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10
}

config2 = {
    'batch_size': 64,
    'dropout': 0.5
}

config3 = {
    'epochs': 20,
    'weight_decay': 0.0001
}

ARGS = {
    'config_list': [config1, config2, config3]
}
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 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
mutate_arch_func_201 Ran
ran on a synthesized input
vita-group/tegnas/R_EA.py
code served (permissive licence) · get_code("d42ce1ace3d15ef3")
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 function. 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 os, sys, time, random, argparse
from copy import deepcopy

# Set random seed for reproducibility
random.seed(0)

# Define a stand-in class for architecture nodes
class StandInArch:
    def __init__(self):
        # nodes is a list where each element is a tuple of tuples
        # Each inner tuple is (operation_name, some_id)
        self.nodes = [
            (("conv", 0), ("relu", 1), ("pool", 2)),
            (("linear", 0), ("conv", 1)),
            (("relu", 0), ("pool", 1), ("linear", 2), ("conv", 3))
        ]

# Define op_names - a list of operation names that can be used
op_names = ["conv", "relu", "pool", "linear", "batch_norm", "dropout"]

ARGS = {
    "op_names": op_names
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
parse_channel_info Ran
ran on a synthesized input
vita-group/tegnas/lib/models/SharedUtils.py
code served (permissive licence) · get_code("d5744b71dab29e1e")
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

def parse_channel_info(xstring):
    blocks = xstring.split(' ')
    blocks = [x.split('-') for x in blocks]
    blocks = [[int(_) for _ in x] for x in blocks]
    return blocks

ARGS = {
    'xstring': '1-2-3 4-5 6-7-8-9'
}
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 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
random_architecture_func_darts Ran
ran on a synthesized input
vita-group/tegnas/R_EA.py
code served (permissive licence) · get_code("d6053d230c2282c0")
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 function. 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 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
from collections import namedtuple

torch.manual_seed(0)

Genotype = namedtuple('Genotype', 'normal normal_concat reduce reduce_concat')

DARTS_SPACE = ['none', 'skip_connect', 'sep_conv_3x3', 'sep_conv_5x5', 'dil_conv_3x3', 'dil_conv_5x5', 'avg_pool_3x3', 'max_pool_3x3']

ARGS = {
    'op_names': DARTS_SPACE
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
select_action Ran
ran on a synthesized input
vita-group/tegnas/reinforce.py
code served (permissive licence) · get_code("d76fd75b329eb07e")
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. 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 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 numpy as np
from torch.distributions import Categorical

torch.manual_seed(0)

class MockPolicy(nn.Module):
    def __init__(self):
        super().__init__()
        # arch_parameters: list of 2 cells, each with parameters for edges
        # Cell structure: 2 edges in block 0, then 3 in block 1, 4 in block 2, 5 in block 3
        # Total edges per cell: 2 + 3 + 4 + 5 = 14
        self.arch_parameters = nn.ParameterList([
            nn.Parameter(torch.randn(14, 4)),  # cell 0: 14 edges, 4 operations
            nn.Parameter(torch.randn(14, 4))   # cell 1: 14 edges, 4 operations
        ])
    
    def forward(self):
        # Return 2 probability distributions (one for each cell)
        # Each should have shape (14, 4) representing logits for 14 edges x 4 operations
        logits_0 = self.arch_parameters[0]  # (14, 4)
        logits_1 = self.arch_parameters[1]  # (14, 4)
        
        probs_0 = torch.nn.functional.softmax(logits_0, dim=-1)  # (14, 4)
        probs_1 = torch.nn.functional.softmax(logits_1, dim=-1)  # (14, 4)
        
        return (probs_0, probs_1)

policy = MockPolicy()

ARGS = {
    "policy": policy
}
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 tuple — a tuple 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
get_datasets Not yet run
unverified (harvested, no recorded run)
vita-group/tegnas/lib/datasets/get_dataset_with_transform.py
code served (permissive licence) · get_code("e886699e0b7d7466")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 6 later) and 8 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
4 dated earlier, 9 later
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
4 dated earlier, 9 later
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
1 dated earlier, 5 later
2001.00326 (2020-01)
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
2205.05662 (2022-05)
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
2207.09639 (2022-07)
DC-BENCH: Dataset Condensation Benchmark
and 3 more not named here
change_key 2 other papers
1 dated earlier, 1 later
2006.16537 (2020-06)
Theory-Inspired Path-Regularized Differential Network Architecture Search
parse_channel_info 2 other papers
1 dated earlier, 1 later
2006.16537 (2020-06)
Theory-Inspired Path-Regularized Differential Network Architecture Search
additive_func 1 other paper
1 later
Sun_Unleashing_the_Power_of_Gradient_Signal-to-Noise_Ratio_for_Zero-Shot_NAS_ICCV_2023_paper (2023 (year only))
Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NAS

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

This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS has been explosively studied to automate the discovery of top-performer neural networks, but suffers from heavy resource consumption and often incurs search bias due to truncated training or approximations. Recent NAS works start to explore indicators that can predict a network's performance without training. However, they either leveraged limited properties of deep networks, or the benefits of their training-free indicators are not applied to more extensive search methods. By rigorous correlation analysis, we present a unified framework to understand and accelerate NAS, by disentangling "TEG" characteristics of searched networks - Trainability, Expressivity, Generalization - all assessed in a training-free manner. The TEG indicators could be scaled up and integrated with various NAS search methods, including both supernet and single-path approaches. Extensive studies validate the effective and efficient guidance from our TEG-NAS framework, leading to both improved search accuracy and over 56% reduction in search time cost. Moreover, we visualize search trajectories on three landscapes of "TEG" characteristics, observing that while a good local minimum is easier to find on NAS-Bench-201 given its simple topology, balancing "TEG" characteristics is much harder on the DARTS search space due to its complex landscape geometry. Our code is available at https://github.com/VITA-Group/TEGNAS.

For agents

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

get_harvested_code_for_paper("2108.11939")
get_code_for_paper("2108.11939")
have("2108.11939")

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

curl https://syntology.ai/api/ran/2108.11939.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.11939.svg)](https://syntology.ai/paper/2108.11939)

Connect an agent — have() is free.