SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.02695 · 2018

Seismic Signal Denoising and Decomposition Using Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

12 of 20 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 12 have no contract verdict; 0 failures of our instrument; 8 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/1811.02695.json · badge: /api/ran/1811.02695.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
wayneweiqiang/quakeflow community (classifier label)
classifier basis not recorded on the link
8 ran · 7 no recorded run
wayneweiqiang/DeepDenoiser community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
calc_azimuth Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/cut_event_hdf5.py
code served (permissive licence) · get_code("0817d05e8c5c3c64")
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 (2,) 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 calc_azimuth takes 4 parameters: lat1, lon1, lat2, lon2
# These are latitude and longitude coordinates that need to be converted to radians
# and processed with trigonometric operations. The function is vectorized, so it
# accepts scalars or arrays.

# Create small numpy arrays to represent coordinate pairs
lat1 = np.array([40.7128, 51.5074])
lon1 = np.array([-74.0060, -0.1278])
lat2 = np.array([34.0522, 48.8566])
lon2 = np.array([-118.2437, 2.3522])

ARGS = {
    "lat1": lat1,
    "lon1": lon1,
    "lat2": lat2,
    "lon2": lon2,
}
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 (2,) — shape (2,) 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
calc_distance_km Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/cut_event_hdf5.py
code served (permissive licence) · get_code("d81a2354bde02db9")
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 (2,) 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 calc_distance_km takes 4 parameters: lat1, lon1, lat2, lon2
# Each should be a scalar or array-like of latitude/longitude values in degrees
# The function uses np.radians, np.sin, np.cos, np.arctan2, np.sqrt, np.round
# These work on scalars and numpy arrays

# Test with arrays of different shapes to show vectorization
lat1 = np.array([40.7128, 51.5074])  # latitudes for NYC and London
lon1 = np.array([-74.0060, -0.1278])  # longitudes for NYC and London
lat2 = np.array([48.8566, 35.6762])  # latitudes for Paris and Tokyo
lon2 = np.array([2.3522, 139.6503])  # longitudes for Paris and Tokyo

ARGS = {
    "lat1": lat1,
    "lon1": lon1,
    "lat2": lat2,
    "lon2": lon2
}
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 (2,) — shape (2,) 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
crop_and_concat Ran
ran on a synthesized input
wayneweiqiang/DeepDenoiser/deepdenoiser/model.py
code served (permissive licence) · get_code("02c35f561051b6fe")
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 EagerTensor, ndim 4, dtype family float, shape (2, 4, 4, 8) 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 tensorflow as tf

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

# Create two tensors with different spatial sizes
# net1 is smaller (4x4 spatial), net2 is larger (6x6 spatial)
# Both have batch dimension of 2
# net1 has 3 channels, net2 has 5 channels
net1 = tf.constant([
    [[[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]],
     [[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]],
     [[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]],
     [[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]]],
    [[[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]],
     [[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]],
     [[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]],
     [[1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0], [1.0, 2.0, 3.0]]]
], dtype=tf.float32)

# net2 has shape [2, 6, 6, 5] - larger spatial dimensions and more channels
net2 = tf.random.normal([2, 6, 6, 5], dtype=tf.float32)

ARGS = {
    "net1": net1,
    "net2": net2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 4, 8) — shape (2, 4, 4, 8) 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
discover_remaining_years Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/launch_build_dataset.py
code served (permissive licence) · get_code("d1bc0b6013b74018")
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, 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
import numpy as np
from unittest.mock import MagicMock

class MockFileSystem:
    """Mock filesystem that simulates s3fs or similar for testing."""
    
    def __init__(self):
        self.structure = {
            'quakeflow_dataset/NCEDC/waveform_parquet': ['2020', '2021', '2022'],
            'quakeflow_dataset/SCEDC/waveform_parquet': ['2019', '2020', '2021', '2022'],
            'quakeflow_dataset/quakeflow_nc/waveform_parquet': ['2020', '2021'],
            'quakeflow_dataset/quakeflow_sc/waveform_parquet': ['2021'],
        }
    
    def ls(self, path, detail=False):
        """List files/directories at path."""
        path = path.rstrip('/')
        if path not in self.structure:
            raise FileNotFoundError(f"Path not found: {path}")
        
        items = self.structure[path]
        if detail:
            return [{'name': item, 'size': 100} for item in items]
        else:
            # Return full paths
            return [f"{path}/{item}" for item in items]


fs = MockFileSystem()

ARGS = {
    'fs': fs
}
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 list, ndim 1, dtype family int — a list 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
extract_event_number Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/build_quakeflow_dataset.py
code served (permissive licence) · get_code("9ebc7570c558d619")
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 re

def extract_event_number(event_id_str):
    """Extract numeric part from event_id (e.g., 'nc12345' -> 12345)."""
    digits = re.sub('[^0-9]', '', event_id_str)
    return int(digits) if digits else 0

ARGS = {
    "event_id_str": "nc12345"
}
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 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
list_parquet_by_year Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/build_quakeflow_dataset.py
code served (permissive licence) · get_code("3bdb92ef4b5b2440")
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 fsspec

# Create a mock filesystem that implements the ls() method
class MockFilesystem:
    def __init__(self):
        self.file_structure = {
            "/data": ["/data/2020", "/data/2021", "/data/2022"],
            "/data/2020": ["/data/2020/file1.parquet", "/data/2020/file2.parquet"],
            "/data/2021": ["/data/2021/file3.parquet"],
            "/data/2022": ["/data/2022/file4.parquet", "/data/2022/file5.parquet", "/data/2022/file6.txt"],
        }
    
    def ls(self, path, detail=False):
        path = path.rstrip('/')
        if path not in self.file_structure:
            raise FileNotFoundError(f"Path {path} not found")
        return self.file_structure[path]

fs = MockFilesystem()
base_path = "/data"

ARGS = {
    "fs": fs,
    "base_path": base_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
fsspec — 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
node_disk_gb Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/launch_parquet_to_hdf5.py
code served (permissive licence) · get_code("400fc1220c7d4415")
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 math

def node_disk_gb(total_parquet_gb):
    """Boot disk: OS+env + one yearly HDF5 (<= parquet) + generous margin."""
    return max(80, math.ceil(total_parquet_gb * 1.6 + 40))

ARGS = {
    "total_parquet_gb": 50
}
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 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
node_ram_gb Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/launch_parquet_to_hdf5.py
code served (permissive licence) · get_code("fcba07d721d30125")
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

torch.manual_seed(0)

ARGS = {
    "busiest_day_gb": 8
}
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
normalize Ran
ran on a synthesized input
wayneweiqiang/DeepDenoiser/deepdenoiser/data_reader.py
code served (permissive licence) · get_code("a03238261c77c7d1")
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 numpy as np
from scipy.interpolate import interp1d

# Create a small test dataset with shape (nsta, chn, nt)
# nsta=2 stations, chn=3 channels, nt=500 time samples
nsta = 2
chn = 3
nt = 500

# Generate random data with reasonable values
np.random.seed(42)
data = np.random.randn(nsta, chn, nt) * 10 + 5

# Define window parameter
window = 200

ARGS = {
    "data": data,
    "window": window,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
normalize_batch Ran
ran on a synthesized input
wayneweiqiang/DeepDenoiser/deepdenoiser/data_reader.py
code served (permissive licence) · get_code("9d55208fc8141e58")
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 4, dtype family float, shape (2, 3, 100, 2) 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

# Create a small test batch of data with shape (nbt, nf, nt, nimg)
# nbt: number of batches = 2
# nf: number of features = 3
# nt: number of time steps = 100
# nimg: number of images = 2
data = np.random.randn(2, 3, 100, 2).astype(np.float32)

ARGS = {
    'data': data,
    'window': 200
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (2, 3, 100, 2) — shape (2, 3, 100, 2) 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
py_func_decorator Ran
ran on a synthesized input
wayneweiqiang/DeepDenoiser/deepdenoiser/data_reader.py
code served (permissive licence) · get_code("e9294c3ecb0f895e")
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 tensorflow as tf

def sample_py_function(x, y):
    """A simple Python function to be wrapped by the decorator."""
    return x + y

def sample_py_function_multi_output(x):
    """A Python function that returns multiple outputs."""
    return x * 2, x + 1

ARGS = {
    "output_types": tf.float32,
    "output_shapes": [tf.TensorShape([2, 3])],
    "name": "test_py_func"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
round_robin Ran
ran on a synthesized input
wayneweiqiang/quakeflow/datasets/launch_build_dataset.py
code served (permissive licence) · get_code("54bf1340d56f0eab")
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

ARGS = {
    "lst": [1, 2, 3, 4, 5, 6, 7],
    "n": 3
}
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
channel_local_depth Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/cut_event_parquet.py
code served (permissive licence) · get_code("c6d91ac8d411ad87")
How it ran

no invocation recorded.

crop_only Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/DeepDenoiser/deepdenoiser/model.py
code served (permissive licence) · get_code("8f3ddc1860a69076")
How it ran

no invocation recorded.

discover_remaining Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/launch_parquet_to_hdf5.py
code served (permissive licence) · get_code("2f64577a451d96a3")
How it ran

no invocation recorded.

load_quakeflow_dataset Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/load_dataset.py
code served (permissive licence) · get_code("983fe9c0088e505b")
How it ran

no invocation recorded.

load_station_csv Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/cut_event_hdf5.py
code served (permissive licence) · get_code("5352ecfe242be179")
How it ran

no invocation recorded.

read_and_filter Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/build_quakeflow_dataset.py
code served (permissive licence) · get_code("c5777d5cabfcc46b")
How it ran

no invocation recorded.

read_parquet_metadata Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/build_quakeflow_catalog.py
code served (permissive licence) · get_code("986152c2d641d8be")
How it ran

no invocation recorded.

waveform_unit Not yet run
unverified (harvested, no recorded run)
wayneweiqiang/quakeflow/datasets/cut_event_parquet.py
code served (permissive licence) · get_code("97349587a81339f6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 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 20 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

Denoising and filtering are widely used in routine seismic-data-processing to improve the signal-to-noise ratio (SNR) of recorded signals and by doing so to improve subsequent analyses. In this paper we develop a new denoising/decomposition method, DeepDenoiser, based on a deep neural network. This network is able to learn simultaneously a sparse representation of data in the time-frequency domain and a non-linear function that maps this representation into masks that decompose input data into a signal of interest and noise (defined as any non-seismic signal). We show that DeepDenoiser achieves impressive denoising of seismic signals even when the signal and noise share a common frequency band. Our method properly handles a variety of colored noise and non-earthquake signals. DeepDenoiser can significantly improve the SNR with minimal changes in the waveform shape of interest, even in presence of high noise levels. We demonstrate the effect of our method on improving earthquake detection. There are clear applications of DeepDenoiser to seismic imaging, micro-seismic monitoring, and preprocessing of ambient noise data. We also note that potential applications of our approach are not limited to these applications or even to earthquake data, and that our approach can be adapted to diverse signals and applications in other settings.

For agents

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

get_harvested_code_for_paper("1811.02695")
get_code_for_paper("1811.02695")
have("1811.02695")

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

curl https://syntology.ai/api/ran/1811.02695.json

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

[![Syntology run record](https://syntology.ai/api/ran/1811.02695.svg)](https://syntology.ai/paper/1811.02695)

Connect an agent — have() is free.