SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.01320 · 2021

An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems

arXiv · PDF · Open in the Atlas

Code that ran

14 of 18 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; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 11 failures of our instrument; 4 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/2104.01320.json · badge: /api/ran/2104.01320.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
yzyouzhang/Empirical-Channel-CM canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
yzyouzhang/AIR-ASVspoof canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
yzyouzhang/asvspoof2021_air community (classifier label)
classifier basis: plan_row
6 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_det_curve Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yzyouzhang/asvspoof2021_air/eval_metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from asvspoof-challenge/2021, is pointer only (licence: NONE) · get_code("3a889d3debbcead8")
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 asvspoof-challenge/2021, 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.

compute_eer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yzyouzhang/asvspoof2021_air/eval_metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from asvspoof-challenge/2021, is pointer only (licence: NONE) · get_code("047cd2d292cdc66d")
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 asvspoof-challenge/2021, 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
yzyouzhang/AIR-ASVspoof/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from guanyuezhen/ufcd, is pointer only (licence: NONE) · get_code("6ef392f365cc5703")
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 guanyuezhen/ufcd, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
yzyouzhang/AIR-ASVspoof/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from amerch/CIFAR100-Training, is pointer only (licence: NONE) · get_code("583f9780bdd00a45")
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 amerch/CIFAR100-Training, 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.

delta Ran
ran; our contract draft was wrong, not the code
yzyouzhang/Empirical-Channel-CM/feature_extraction.py
code served (permissive licence) · get_code("cf8271127e8f0134")
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 3, dtype family float, shape (2, 5, 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)

# The function takes a single parameter 'x' which should be a tensor
# with shape (batch, Length, dim)
# Based on the docstring and function body:
# - x is used with .shape[1] to get Length
# - x is unsqueezed to add dimension, padded, and squeezed back
# - Operations are performed along the Length dimension

# Create a small test tensor with distinct dimensions:
# batch=2, Length=5, dim=4
x = torch.randn(2, 5, 4)

ARGS = {
    'x': x
}
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 3, dtype family float, shape (2, 5, 4) — shape (2, 5, 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
float_2_label Ran
ran; our contract draft was wrong, not the code
yzyouzhang/Empirical-Channel-CM/utils_dsp.py
code served (permissive licence) · get_code("15dd14c88916880d")
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 a small float tensor with values in a reasonable range
x = torch.randn(2, 4) * 0.5  # Values roughly in [-1, 1] range
bits = 8

ARGS = {
    "x": x,
    "bits": bits,
}
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
label_2_float Ran
ran, honoured the contract we drafted
yzyouzhang/Empirical-Channel-CM/utils_dsp.py
code served (permissive licence) · get_code("7453b30a6a37676b")
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
import numpy as np

torch.manual_seed(0)

# The function takes:
# x: a tensor of integer values (long or int), any shape
# bits: number of bits (int)

# Create a small tensor with integer values
x = torch.tensor([[0, 1, 2, 3], [4, 5, 6, 7]], dtype=torch.long)

# Set bits to a reasonable value
bits = 8

ARGS = {
    "x": x,
    "bits": bits
}
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 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
mulaw_encode Ran
ran; our contract draft was wrong, not the code
yzyouzhang/Empirical-Channel-CM/utils_dsp.py
code served (permissive licence) · get_code("8dd719296048d271")
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 int, 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 a small float-valued waveform tensor in (-1, 1)
# Shape: (2, 4) - batch size 2, 4 samples
x = torch.randn(2, 4) * 0.5  # scale to be roughly in (-1, 1)

# Number of quantization channels
quantization_channels = 256

# Boolean flag for scaling to int
scale_to_int = True

ARGS = {
    "x": x,
    "quantization_channels": quantization_channels,
    "scale_to_int": scale_to_int,
}
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 int, 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
obtain_asv_error_rates Ran
ran; our contract draft was wrong, not the code
yzyouzhang/asvspoof2021_air/eval_metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from xjchengit/singgraph, is pointer only (licence: NONE) · get_code("4a9fc5f1de58c879")
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 xjchengit/singgraph, 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.

padding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yzyouzhang/AIR-ASVspoof/dataset.py
code served (permissive licence) · get_code("52f297b90a82ab25")
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 (4, 5) 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)

# spec: a tensor with shape (width, cur_len)
# The function accesses spec.shape, spec.dtype, and concatenates along dimension 1
# ref_len: an integer greater than cur_len

spec = torch.randn(4, 2)  # width=4, cur_len=2
ref_len = 5  # must be > cur_len (which is 2)

ARGS = {
    "spec": spec,
    "ref_len": ref_len,
}
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 (4, 5) — shape (4, 5) 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
padding_Tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yzyouzhang/Empirical-Channel-CM/dataset.py
code served (permissive licence) · get_code("f0a1f94179d20efb")
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 3, dtype family float, shape (1, 5, 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)

# Construct a small 3D tensor with shape (batch=1, seq_len=2, width=4)
# The function expects spec.shape to unpack as (_, cur_len, width)
spec = torch.randn(1, 2, 4)

# ref_len must be greater than cur_len (which is 2)
ref_len = 5

ARGS = {
    "spec": spec,
    "ref_len": ref_len,
}
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 3, dtype family float, shape (1, 5, 4) — shape (1, 5, 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
read_file Ran
ran on a synthesized input
yzyouzhang/asvspoof2021_air/score_fusion.py
code served (permissive licence) · get_code("c331f51bee478856")
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 DataFrame. 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 numpy as np
import pandas as pd
import tempfile
import os

# Create a temporary CSV file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, 'test_data.txt')

# Write test data to the temporary file
test_data = np.array([
    ['file1', 'sys001', 'key_a', '0.95'],
    ['file2', 'sys002', 'key_b', '0.87'],
    ['file3', 'sys003', 'key_c', '0.76']
])

np.savetxt(temp_file, test_data, fmt='%s', delimiter=' ')

ARGS = {
    'fname': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
repeat_padding_Tensor Ran
ran; our contract draft was wrong, not the code
yzyouzhang/asvspoof2021_air/dataset.py
code served (permissive licence) · get_code("14738aac076461dd")
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 3, dtype family float, shape (2, 7, 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
import numpy as np

torch.manual_seed(0)

# The function takes a spec tensor and ref_len integer
# spec is accessed with .shape[1] and .repeat(1, mul, 1) operations
# This suggests spec is a 3D tensor with shape (batch, time, features)

spec = torch.randn(2, 3, 4)  # (batch=2, time=3, features=4)
ref_len = 7  # A reference length to pad/repeat to

ARGS = {
    "spec": spec,
    "ref_len": ref_len
}
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 Tensor, ndim 3, dtype family float, shape (2, 7, 4) — shape (2, 7, 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
shuffle Ran
ran on a synthesized input
yzyouzhang/asvspoof2021_air/main_train.py
code served (permissive licence) · get_code("6e88ac6fb45d54ef")
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. 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)

# Create small tensors for the function parameters
feat = torch.randn(2, 4)  # batch size 2, feature dim 4
tags = torch.randint(0, 5, (2,))  # batch size 2, integer tags
labels = torch.randint(0, 3, (2,))  # batch size 2, integer labels

ARGS = {
    "feat": feat,
    "tags": tags,
    "labels": labels,
}
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 — 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
avg_fuse Not yet run
unverified (harvested, no recorded run)
yzyouzhang/asvspoof2021_air/score_fusion.py
code served (permissive licence) · get_code("23f88914dbfe49d4")
How it ran

no invocation recorded.

repeat_padding Not yet run
unverified (harvested, no recorded run)
yzyouzhang/AIR-ASVspoof/dataset.py
code served (permissive licence) · get_code("e976b5d8227e655a")
How it ran

no invocation recorded.

trimf Not yet run
unverified (harvested, no recorded run)
yzyouzhang/Empirical-Channel-CM/feature_extraction.py
code served (permissive licence) · get_code("a2e29dbb85083b43")
How it ran

no invocation recorded.

weighted_fuse Not yet run
unverified (harvested, no recorded run)
yzyouzhang/asvspoof2021_air/score_fusion.py
code served (permissive licence) · get_code("d743cf58be5e7fa6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 7 later) and 11 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
285 dated earlier, 19 the same month, 376 later, 6 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
conv1x1 431 other papers
114 dated earlier, 13 the same month, 298 later, 5 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
compute_det_curve 8 other papers
2 dated earlier, 6 later
1904.05441 (2019-04)
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
2011.01108 (2020-11)
End-to-end anti-spoofing with RawNet2
2110.01200 (2021-10)
AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
and 5 more not named here
compute_eer 6 other papers
1 dated earlier, 5 later
2011.01108 (2020-11)
End-to-end anti-spoofing with RawNet2
2210.02437 (2022-10)
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
2309.07525 (2023-09)
SingFake: Singing Voice Deepfake Detection
and 3 more not named here
obtain_asv_error_rates 5 other papers
2 dated earlier, 3 later
1904.05441 (2019-04)
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
2011.01108 (2020-11)
End-to-end anti-spoofing with RawNet2
2110.01200 (2021-10)
AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
and 2 more not named here
label_2_float 1 other paper
1 later
2309.07525 (2023-09)
SingFake: Singing Voice Deepfake Detection
repeat_padding_Tensor 1 other paper
1 later
2309.07525 (2023-09)
SingFake: Singing Voice Deepfake Detection

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

Spoofing countermeasure (CM) systems are critical in speaker verification; they aim to discern spoofing attacks from bona fide speech trials. In practice, however, acoustic condition variability in speech utterances may significantly degrade the performance of CM systems. In this paper, we conduct a cross-dataset study on several state-of-the-art CM systems and observe significant performance degradation compared with their single-dataset performance. Observing differences of average magnitude spectra of bona fide utterances across the datasets, we hypothesize that channel mismatch among these datasets is one important reason. We then verify it by demonstrating a similar degradation of CM systems trained on original but evaluated on channel-shifted data. Finally, we propose several channel robust strategies (data augmentation, multi-task learning, adversarial learning) for CM systems, and observe a significant performance improvement on cross-dataset experiments.

For agents

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

get_harvested_code_for_paper("2104.01320")
get_code_for_paper("2104.01320")
have("2104.01320")

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

curl https://syntology.ai/api/ran/2104.01320.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.01320.svg)](https://syntology.ai/paper/2104.01320)

Connect an agent — have() is free.