SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.13293 · ICML · 2021

KNAS: Green Neural Architecture Search

Liang Zhao, Jingjing Xu, Junyang Lin, Hongxia Yang, Xu Sun, Rundong Gao

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 (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 1 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/2111.13293.json · badge: /api/ran/2111.13293.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
jingjing-nlp/knas community
Papers with Code archive
6 ran · 1 no recorded run
FunctionStatusWhere it lives
DualSepConv Ran
ran on a synthesized input · constructed an object; no result was computed
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("1e18a8f367b94a9d")
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 an instance of its own class, DualSepConv: the run constructed the object and did not call it, so no result was computed. 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)

# Define ARGS dict with all parameters for DualSepConv
ARGS = {
    'C_in': 3,
    'C_out': 16,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'dilation': 1,
    'affine': True,
    'track_running_stats': 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 DualSepConv — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DualSepConv 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
FactorizedReduce Ran
ran on a synthesized input · constructed an object; no result was computed
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("7c0ac1e94a87f10f")
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 an instance of its own class, FactorizedReduce: the run constructed the object and did not call it, so no result was computed. 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)

# Define arguments for FactorizedReduce
ARGS = {
    'C_in': 4,           # input channels
    'C_out': 8,          # output channels
    'stride': 2,         # stride value (can be 1 or 2)
    'affine': True,      # whether to use affine in BatchNorm2d
    'track_running_stats': True  # whether to track running stats in BatchNorm2d
}
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 FactorizedReduce — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FactorizedReduce 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
POOLING Ran
ran on a synthesized input · constructed an object; no result was computed
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("7e1ed06de24336a1")
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 an instance of its own class, POOLING: the run constructed the object and did not call it, so no result was computed. 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)

# Construct ARGS dict with all parameters for POOLING
ARGS = {
    'C_in': 4,
    'C_out': 8,
    'stride': 2,
    'mode': 'avg',
    'affine': True,
    'track_running_stats': 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 POOLING — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a POOLING 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
ReLUConvBN Ran
ran on a synthesized input · constructed an object; no result was computed
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("ce76eaaf23f7764b")
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 an instance of its own class, ReLUConvBN: the run constructed the object and did not call it, so no result was computed. 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 = {
    'C_in': 3,
    'C_out': 16,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'dilation': 1,
    'affine': True,
    'track_running_stats': 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 ReLUConvBN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ReLUConvBN 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
SepConv Ran
ran on a synthesized input · constructed an object; no result was computed
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("3eaf4c1a73aca5f0")
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 an instance of its own class, SepConv: the run constructed the object and did not call it, so no result was computed. 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 = {
    'C_in': 3,
    'C_out': 16,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'dilation': 1,
    'affine': True,
    'track_running_stats': 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 SepConv — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SepConv 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
Zero Ran
ran on a synthesized input · constructed an object; no result was computed
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("241a3f0cda58125e")
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 an instance of its own class, Zero: the run constructed the object and did not call it, so no result was computed. 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)

class Zero(nn.Module):
    def __init__(self, C_in, C_out, stride):
        super(Zero, self).__init__()
        self.C_in = C_in
        self.C_out = C_out
        self.stride = stride
        self.is_zero = True

    def forward(self, x):
        if self.C_in == self.C_out:
            if self.stride == 1:
                return x.mul(0.0)
            else:
                return x[:, :, ::self.stride, ::self.stride].mul(0.0)
        else:
            shape = list(x.shape)
            shape[1] = self.C_out
            zeros = x.new_zeros(shape, dtype=x.dtype, device=x.device)
            return zeros

    def extra_repr(self):
        return 'C_in={C_in}, C_out={C_out}, stride={stride}'.format(**self.__dict__)

ARGS = {
    'C_in': 4,
    'C_out': 3,
    'stride': 2
}
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 Zero — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Zero 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
NAS201SearchCell Not yet run
unverified (harvested, no recorded run)
jingjing-nlp/knas/lib/models/cell_searchs/search_cells.py
code served (permissive licence) · get_code("953c6960d5b84981")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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

Many existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations. Considering that these computations bring a large carbon footprint, this paper aims to explore a green (namely environmental-friendly) NAS solution that evaluates architectures without training. Intuitively, gradients, induced by the architecture itself, directly decide the convergence and generalization results. It motivates us to propose the gradient kernel hypothesis: Gradients can be used as a coarse-grained proxy of downstream training to evaluate random-initialized networks. To support the hypothesis, we conduct a theoretical analysis and find a practical gradient kernel that has good correlations with training loss and validation performance. According to this hypothesis, we propose a new kernel based architecture search approach KNAS. Experiments show that KNAS achieves competitive results with orders of magnitude faster than "train-then-test" paradigms on image classification tasks. Furthermore, the extremely low search cost enables its wide applications. The searched network also outperforms strong baseline RoBERTA-large on two text classification tasks. Codes are available at https: //github.com/Jingjing-NLP/KNAS.

For agents

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

get_harvested_code_for_paper("2111.13293")
get_code_for_paper("2111.13293")
have("2111.13293")

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

curl https://syntology.ai/api/ran/2111.13293.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.13293.svg)](https://syntology.ai/paper/2111.13293)

Connect an agent — have() is free.