SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.03154 · 2020

Discretization-Aware Architecture Search

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 5 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2007.03154.json · badge: /api/ran/2007.03154.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
sunsmarterjie/DAAS canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
exp Ran
ran on a synthesized input
sunsmarterjie/DAAS/cnn/dimension.py
code served (permissive licence) · get_code("135e8cf8c541a30f")
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 float, 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 torch
import numpy as np

EP = 50

def exp(epoch):
    return 2 ** (epoch / 5) / 2 ** (EP / 5 - 1) / 2

# The function takes a single parameter 'epoch' which is used in arithmetic operations
# It should be a numeric value (int or float)

ARGS = {
    "epoch": 10
}
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 float, 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
linear Ran
ran on a synthesized input
sunsmarterjie/DAAS/cnn/dimension.py
code served (permissive licence) · get_code("f3c362e9fc95f547")
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 float, 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 torch

torch.manual_seed(0)

EP = 50

def linear(epoch):
    return 1 / (EP - 1) * (epoch - 1)

ARGS = {
    "epoch": 25
}
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 float, 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
log Ran
ran on a synthesized input
sunsmarterjie/DAAS/cnn/dimension.py
code served (permissive licence) · get_code("175f62423e47edfa")
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 float, 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 math

EP = 50

def log(epoch):
    return math.log(epoch, EP)

# The function takes a single parameter 'epoch' and computes the logarithm
# with base EP (50). The epoch parameter should be a number greater than 1
# to avoid domain errors in logarithm calculation.

ARGS = {
    "epoch": 10
}
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 float, 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
streng_func Ran
ran on a synthesized input
sunsmarterjie/DAAS/cnn/MinEntropyLoss.py
code served (permissive licence) · get_code("15b184c4c625c5c2")
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. 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, 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 takes a tensor t and performs operations on it
# It uses .float(), .cuda(), torch.pow(), and torch.mul()
# We need to pass a tensor that will work with these operations

t = torch.randn(2, 4)

ARGS = {
    "t": t
}
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
streng_func2 Ran
ran on a synthesized input
sunsmarterjie/DAAS/cnn/MinEntropyLoss.py
code served (permissive licence) · get_code("9da5383e082d5b90")
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. 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, 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 takes a tensor t, applies conditional logic based on values,
# and returns a modified tensor. It uses .cuda() internally, which will fail,
# but we construct valid input anyway.

t = torch.randn(2, 4)

ARGS = {
    "t": t
}
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
accuracy Not yet run
unverified (harvested, no recorded run)
sunsmarterjie/DAAS/cnn/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuxwind/exactcompression, is pointer only (licence: NONE) · get_code("469bf48752905889")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuxwind/exactcompression, 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.

count_parameters_in_MB Not yet run
unverified (harvested, no recorded run)
sunsmarterjie/DAAS/cnn/utils.py
code served (permissive licence) · get_code("3e816289579cc9e9")
How it ran

no invocation recorded.

drop_path Not yet run
unverified (harvested, no recorded run)
sunsmarterjie/DAAS/cnn/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hyeonjeongha/croze, is pointer only (licence: NONE) · get_code("13c2719404e25b25")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from hyeonjeongha/croze, 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 5 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
accuracy 71 other papers
35 dated earlier, 4 the same month, 32 later · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
and 68 more not named here
count_parameters_in_MB 8 other papers
4 dated earlier, 1 the same month, 3 later
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1912.00195 (2019-12)
SGAS: Sequential Greedy Architecture Search
2004.14557 (2020-04)
Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
and 5 more not named here
drop_path 6 other papers
3 dated earlier, 1 the same month, 2 later
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1912.00195 (2019-12)
SGAS: Sequential Greedy Architecture Search
2006.16537 (2020-06)
Theory-Inspired Path-Regularized Differential Network Architecture Search
and 3 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods. These methods optimize a super-network with all possible edges and operations, and determine the optimal sub-network by discretization, \textit{i.e.}, pruning off weak candidates. The discretization process, performed on either operations or edges, incurs significant inaccuracy and thus the quality of the final architecture is not guaranteed. This paper presents discretization-aware architecture search (DA\textsuperscript{2}S), with the core idea being adding a loss term to push the super-network towards the configuration of desired topology, so that the accuracy loss brought by discretization is largely alleviated. Experiments on standard image classification benchmarks demonstrate the superiority of our approach, in particular, under imbalanced target network configurations that were not studied before.

For agents

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

get_harvested_code_for_paper("2007.03154")
get_code_for_paper("2007.03154")
have("2007.03154")

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

curl https://syntology.ai/api/ran/2007.03154.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.03154.svg)](https://syntology.ai/paper/2007.03154)

Connect an agent — have() is free.