SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02286 · 2026

DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wild

Sebastian Möller, Yassine Kheir, Arnab Das, Enes Erdogan, Feidi Kallel, Tim Polzehl

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 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/2602.02286.json · badge: /api/ran/2602.02286.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
IDRnD/redimnet canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
custom_partial Ran
ran; our contract draft was wrong, not the code
IDRnD/redimnet/redimnet/model.py
code served (permissive licence) · get_code("024135072cc99987")
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)

def sample_function(a, b, c=10):
    """A sample function to be wrapped by custom_partial"""
    return a + b + c

# Define fixed keyword arguments
fixed_kwargs = {"c": 20}

# Create the wrapper using custom_partial
def custom_partial(func, **fixed_kwargs):
    def wrapper(**kwargs):
        merged_kwargs = {**fixed_kwargs, **kwargs}
        return func(**merged_kwargs)
    return wrapper

# Test the setup
wrapper_func = custom_partial(sample_function, **fixed_kwargs)

ARGS = {
    "func": sample_function,
    "fixed_kwargs": {"c": 20}
}
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
gelu Ran
ran; our contract draft was wrong, not the code
IDRnD/redimnet/redimnet/layers/attention.py
code served (permissive licence) · get_code("88607e3bd7f9b5be")
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 math

torch.manual_seed(0)

# The function gelu takes a single parameter x which should be a torch tensor
# The function applies element-wise operations: multiplication, addition, and torch.erf
x = torch.randn(2, 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 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
get_filterbanks Ran
ran, honoured the contract we drafted
IDRnD/redimnet/redimnet/layers/features_tf.py
code served (permissive licence) · get_code("711dfabf485d6263")
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 ndarray, ndim 2, dtype family float, shape (512, 80) 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 numpy as np

# The function get_filterbanks takes the following parameters:
# - low_freq: int (default 20)
# - high_freq: int (default 7600)
# - nfilt: int (default 80)
# - nfft: int (default 512)
# - samplerate: int (default 16000)

# All parameters are integers with sensible defaults.
# Let's create a small set of arguments that will execute the function.

ARGS = {
    'low_freq': 20,
    'high_freq': 7600,
    'nfilt': 80,
    'nfft': 512,
    'samplerate': 16000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (512, 80) — shape (512, 80) 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
hz2mel Ran
ran, violated the contract we drafted
IDRnD/redimnet/redimnet/layers/features_tf.py
code served (permissive licence) · get_code("3d0e2c23ed984f7c")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

# hz2mel takes a single parameter 'hz' which can be:
# - a scalar value in Hertz
# - a numpy array of values in Hertz
# The function converts element-wise using the formula: 2595 * np.log10(1 + hz / 700.0)

# Create test data: a numpy array of Hz values
hz_values = np.array([100.0, 440.0, 1000.0, 8000.0])

ARGS = {
    'hz': hz_values
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
mel2hz Ran
ran, violated the contract we drafted
IDRnD/redimnet/redimnet/layers/features_tf.py
code served (permissive licence) · get_code("a45993bbee34006f")
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 ndarray, ndim 1, dtype family float, shape (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)

# mel2hz takes a mel value and converts it to Hz
# The parameter can be a scalar, numpy array, or torch tensor
# The function performs element-wise arithmetic operations on it

# Test with different input types:
# 1. Scalar float
mel_scalar = 100.0

# 2. Numpy array
mel_numpy = np.array([0.0, 50.0, 100.0, 150.0])

# 3. Torch tensor
mel_tensor = torch.tensor([10.0, 20.0, 30.0, 40.0])

# The function will work with any of these
ARGS = {
    "mel": mel_numpy
}
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 ndarray, ndim 1, dtype family float, shape (4,) — shape (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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
gelu 198 other papers
190 dated earlier, 8 later · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 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 2026-11-22.

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 paper presents the DFKI-Speech system developed for the WildSpoof Challenge under the Spoofing-aware Automatic Speaker Verification (SASV) track. We propose a robust SASV framework in which a spoofing detector and a speaker verification (SV) network operate in tandem. The spoofing detector employs a self-supervised speech embedding extractor as the frontend, combined with a state-of-the-art graph neural network backend. In addition, a top-3 layer-based mixture-of-experts (MoE) is used to fuse high-level and low-level features for effective spoofed utterance detection. For speaker verification, we adapt a lowcomplexity convolutional neural network that fuses 2D and 1D features at multiple scales, trained with the SphereFace loss. Additionally, contrastive circle loss is applied to adaptively weight positive and negative pairs within each training batch, enabling the network to better distinguish between hard and easy sample pairs. Finally, fixed imposter cohort-based AS-Norm score normalization and model ensembling are used to further enhance the discriminative capability of the speaker verification system.

For agents

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

get_harvested_code_for_paper("2602.02286")
get_code_for_paper("2602.02286")
have("2602.02286")

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

curl https://syntology.ai/api/ran/2602.02286.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02286.svg)](https://syntology.ai/paper/2602.02286)

Connect an agent — have() is free.