SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.08138 · 2020

An Open source Implementation of ITU-T Recommendation P.808 with Validation

arXiv · PDF · Open in the Atlas

Code that ran

17 of 21 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 17 have no contract verdict; 0 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/2005.08138.json · badge: /api/ran/2005.08138.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
microsoft/P.808 canonical (classifier label)
classifier basis: census
17 ran · 4 no recorded run
FunctionStatusWhere it lives
active_speech_level_dbov Ran
ran on a synthesized input
microsoft/P.808/src/utils/create_bandwidth_check_clips.py
code served (permissive licence) · get_code("e88fec7c0329bda1")
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 float64, ndim 0, dtype family float; 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 numpy as np

# Create a simple audio signal in range [-1, 1]
# Using a 1-second signal at 16kHz sample rate
sr = 16000
duration_sec = 1.0
num_samples = int(sr * duration_sec)

# Generate a sine wave at 440 Hz with some amplitude variation
t = np.linspace(0, duration_sec, num_samples)
# Mix in a quiet section and a loud section to test active speech detection
signal = np.zeros(num_samples)
signal[:num_samples//2] = 0.1 * np.sin(2 * np.pi * 440 * t[:num_samples//2])  # quiet part
signal[num_samples//2:] = 0.7 * np.sin(2 * np.pi * 440 * t[num_samples//2:])  # loud part

# Ensure signal is in valid range [-1, 1]
signal = np.clip(signal, -1.0, 1.0).astype(np.float32)

ARGS = {
    'signal': signal,
    'sr': sr,
    'frame_ms': 20.0,
    'threshold_db': 25.0,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
add_background_noise Ran
ran on a synthesized input
microsoft/P.808/src/create_gold_clips.py
code served (permissive licence) · get_code("e7b53d1bd52460bb")
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 (16000,) 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
from scipy.signal import butter, lfilter

# Set random seed for reproducibility
np.random.seed(0)

# Create a clean audio signal (small, synthetic)
# Signal parameters
n_samples = 16000  # 1 second at 16kHz sample rate
sr = 16000  # Sample rate in Hz

# Generate a simple synthetic signal (e.g., sine wave)
t = np.linspace(0, 1, n_samples, endpoint=False)
signal = 0.5 * np.sin(2 * np.pi * 440 * t)  # 440 Hz sine wave

# Define arguments for add_background_noise
ARGS = {
    'signal': signal,
    'sr': sr,
    'snr_db': -5.0
}
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 1, dtype family float, shape (16000,) — shape (16000,) 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
apply_signal_distortion Ran
ran on a synthesized input
microsoft/P.808/src/create_gold_clips.py
code served (permissive licence) · get_code("75759035bd91fc72")
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 (16000,) 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 audio signal as a numpy array
signal = np.random.randn(16000).astype(np.float32)

# Define arguments for apply_signal_distortion
ARGS = {
    "signal": signal,
    "clip_threshold": 0.005,
}
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 (16000,) — shape (16000,) 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
check_last_subjective_test Ran
ran on a synthesized input
microsoft/P.808/src/process_qualification_ans.py
code served (permissive licence) · get_code("215b698494381522")
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 bool, 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.

config = {'acceptance_criteria': {'consider_fileds': ['3_mother_tongue', '4_ld', '7_working_area', '8_hearing'], 'correct_hearing_test_bigger_equal': 3}, '3_mother_tongue': ['english', 'en'], '4_ld': ['in-ear', 'over-ear'], '5_last_subjective': ['7d', '30d', 'nn'], '6_audio_test': ['7d', '30d', 'nn'], '7_working_area': ['N'], '8_hearing': ['normal'], 'hearing_test': {'num1': '289', 'num2': '246', 'num3': '626', 'num4': '802', 'num5': '913'}}

def check_last_subjective_test(ans):
    """
    check if the last_subjective_test performed by user was far enough
    """
    return ans in config['5_last_subjective']

ARGS = {
    'ans': '7d'
}
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 bool, 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
check_listening_device Ran
ran on a synthesized input
microsoft/P.808/src/process_qualification_ans.py
code served (permissive licence) · get_code("ead9249c30d8a2b0")
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 bool, 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.

config = {'acceptance_criteria': {'consider_fileds': ['3_mother_tongue', '4_ld', '7_working_area', '8_hearing'], 'correct_hearing_test_bigger_equal': 3}, '3_mother_tongue': ['english', 'en'], '4_ld': ['in-ear', 'over-ear'], '5_last_subjective': ['7d', '30d', 'nn'], '6_audio_test': ['7d', '30d', 'nn'], '7_working_area': ['N'], '8_hearing': ['normal'], 'hearing_test': {'num1': '289', 'num2': '246', 'num3': '626', 'num4': '802', 'num5': '913'}}

ARGS = {
    'ans': 'in-ear headphones'
}
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 bool, 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
check_mother_tongue Ran
ran on a synthesized input
microsoft/P.808/src/process_qualification_ans.py
code served (permissive licence) · get_code("e668d00f5d997ea8")
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 bool, 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.

# Construct valid arguments for check_mother_tongue function

config = {
    'acceptance_criteria': {
        'consider_fileds': ['3_mother_tongue', '4_ld', '7_working_area', '8_hearing'],
        'correct_hearing_test_bigger_equal': 3
    },
    '3_mother_tongue': ['english', 'en'],
    '4_ld': ['in-ear', 'over-ear'],
    '5_last_subjective': ['7d', '30d', 'nn'],
    '6_audio_test': ['7d', '30d', 'nn'],
    '7_working_area': ['N'],
    '8_hearing': ['normal'],
    'hearing_test': {
        'num1': '289',
        'num2': '246',
        'num3': '626',
        'num4': '802',
        'num5': '913'
    }
}

# The function check_mother_tongue takes one parameter: ans
# It checks if ans.strip().lower() is in config['3_mother_tongue']
# So ans should be a string that when stripped and lowercased matches one of the valid values

ARGS = {
    'ans': '  English  '
}
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 bool, 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
conv_filename_to_condition Ran
ran on a synthesized input
microsoft/P.808/src/create_input.py
code served (permissive licence) · get_code("9907d254ba4dd07a")
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 OrderedDict. 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 re
import collections

# Clear the global state from previous runs
file_to_condition_map = {}

# Define test arguments for conv_filename_to_condition
f_name = "experiment_condition_A_trial_01.txt"
condition_pattern = r"experiment_(?P<condition>\w+)_trial_(?P<trial>\d+)\.txt"

ARGS = {
    "f_name": f_name,
    "condition_pattern": condition_pattern,
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
generate_pink_noise Ran
ran on a synthesized input
microsoft/P.808/src/create_gold_clips.py
code served (permissive licence) · get_code("3849af706ed5ed7c")
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 (1000,) 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
from scipy.signal import butter, lfilter

# Set random seed for reproducibility
np.random.seed(0)

ARGS = {
    "n_samples": 1000,
    "sr": 22050,
}
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 1, dtype family float, shape (1000,) — shape (1000,) 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_encoded_gold_ans Ran
ran on a synthesized input
microsoft/P.808/src/master_script.py
code served (permissive licence) · get_code("5ff16b3827081645")
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 str. 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 base64

def get_encoded_gold_ans(url, ans):
    ans = f'{url}_{round(ans)}'
    return base64.b64encode(ans.encode('ascii')).decode('ascii')

ARGS = {
    'url': 'https://example.com/model',
    'ans': 42.7
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
normalize_to_dbfs Ran
ran on a synthesized input
microsoft/P.808/src/utils/create_jnd_check_clips.py
code served (permissive licence) · get_code("710e73f2301ec75e")
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 (100,) 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 simple audio signal as a numpy array
# Using a sine wave with some amplitude
signal = np.sin(np.linspace(0, 2 * np.pi, 100)) * 0.5

# Target dBFS level (typical values range from -20 to -3)
target_dbfs = -10.0

ARGS = {
    "signal": signal,
    "target_dbfs": target_dbfs,
}
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 (100,) — shape (100,) 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
outliers_modified_z_score Ran
ran on a synthesized input
microsoft/P.808/src/result_parser.py
code served (permissive licence) · get_code("977672f85d76ee83")
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 float; 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 numpy as np
import sys

# The function takes votes as input
# votes should be array-like of numeric values
# The function computes median, deviations, and filters based on modified z-score

# Create a small test dataset with some normal values and some outliers
votes = np.array([1.0, 2.0, 1.5, 2.1, 1.8, 100.0, 2.2])

ARGS = {
    "votes": votes
}
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 list, ndim 1, dtype family float — 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
outliers_z_score Ran
ran on a synthesized input
microsoft/P.808/src/result_parser.py
code served (permissive licence) · get_code("88aa2735cc86e2c0")
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 float; 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 statistics
import numpy as np
from scipy import stats

# Test case 1: Normal list with some outliers
votes_with_outliers = [1.0, 2.0, 1.5, 2.1, 1.8, 100.0, 2.2, 1.9]

ARGS = {
    "votes": votes_with_outliers
}
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 list, ndim 1, dtype family float — 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
rel_path Ran
ran on a synthesized input
microsoft/P.808/src/result_parser.py
code served (permissive licence) · get_code("66305b6c700495fc")
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 str. 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 os
import tempfile

# The function rel_path takes one parameter: p (a file path)
# Looking at the function body:
# - It tries to compute os.path.relpath(p, base) where base is _base_dir or os.getcwd()
# - If that fails (ValueError, TypeError), it returns os.path.basename(str(p))
# So p should be a string representing a file path

# Create a temporary file path to use as input
temp_dir = tempfile.gettempdir()
test_file_path = os.path.join(temp_dir, "test_file.txt")

ARGS = {
    "p": test_file_path
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
rms Ran
ran on a synthesized input
microsoft/P.808/src/utils/create_bandwidth_check_clips.py
code served (permissive licence) · get_code("7c90db5cb9981e1a")
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 numpy as np

# Create a simple audio signal as a numpy array
signal = np.array([0.1, 0.2, -0.15, 0.25, -0.1, 0.05, 0.3, -0.2])

ARGS = {
    "signal": signal
}
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 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
scale_to_dbov Ran
ran on a synthesized input
microsoft/P.808/src/utils/create_bandwidth_check_clips.py
code served (permissive licence) · get_code("56c0e3f3a494ebfd")
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 (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 numpy as np

# Create a simple audio signal
signal = np.array([0.1, -0.2, 0.15, -0.05, 0.08, -0.12, 0.09, -0.11], dtype=np.float32)

# Define target dBov level
target_dbov = -20.0

ARGS = {
    "signal": signal,
    "target_dbov": target_dbov,
}
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 (8,) — shape (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
snr_mixer Ran
ran on a synthesized input
microsoft/P.808/src/utils/create_jnd_check_clips.py
code served (permissive licence) · get_code("d5407098010eab79")
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 (16000,) 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

# Set random seeds for reproducibility
np.random.seed(0)

# Create small test signals
# clean: speech signal
clean = np.random.randn(16000).astype(np.float32)

# noise: noise signal (same length as clean)
noise = np.random.randn(16000).astype(np.float32)

# snr: target signal-to-noise ratio in dB
snr = 10.0

# target_level_dbfs: target RMS level in dBFS (optional parameter with default)
target_level_dbfs = -25.0

ARGS = {
    "clean": clean,
    "noise": noise,
    "snr": snr,
    "target_level_dbfs": target_level_dbfs,
}
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 (16000,) — shape (16000,) 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
update_gold_clips_for_personalized Ran
ran on a synthesized input
microsoft/P.808/src/master_script.py
code served (permissive licence) · get_code("dbd5dc9894a7d943")
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 base64
import pandas as pd
import math

ARGS = {
    'df_gold': pd.DataFrame({
        'gold_url': ['http://example.com/clip1', 'http://example.com/clip2'],
        'sig_ans': [42.7, 18.3],
        'bak_ans': [35.2, 22.9],
        'ovrl_ans': [40.1, 20.5],
        'ver': ['v1', 'v2']
    })
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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
add_clips_balanced_block Not yet run
unverified (harvested, no recorded run)
microsoft/P.808/src/create_input.py
code served (permissive licence) · get_code("c2e664e9c05dee61")
How it ran

no invocation recorded.

create_input_for_acr Not yet run
unverified (harvested, no recorded run)
microsoft/P.808/src/create_input.py
code served (permissive licence) · get_code("9138fb8858a1a02d")
How it ran

no invocation recorded.

speech_stats_for_audio Not yet run
unverified (harvested, no recorded run)
microsoft/P.808/src/utils/detect_silence_vad.py
code served (permissive licence) · get_code("958cb86721b252f3")
How it ran

no invocation recorded.

update_gold_clips_for_p804 Not yet run
unverified (harvested, no recorded run)
microsoft/P.808/src/master_script.py
code served (permissive licence) · get_code("7ba5f9e783c82e4a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 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 21 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

The ITU-T Recommendation P.808 provides a crowdsourcing approach for conducting a subjective assessment of speech quality using the Absolute Category Rating (ACR) method. We provide an open-source implementation of the ITU-T Rec. P.808 that runs on the Amazon Mechanical Turk platform. We extended our implementation to include Degradation Category Ratings (DCR) and Comparison Category Ratings (CCR) test methods. We also significantly speed up the test process by integrating the participant qualification step into the main rating task compared to a two-stage qualification and rating solution. We provide program scripts for creating and executing the subjective test, and data cleansing and analyzing the answers to avoid operational errors. To validate the implementation, we compare the Mean Opinion Scores (MOS) collected through our implementation with MOS values from a standard laboratory experiment conducted based on the ITU-T Rec. P.800. We also evaluate the reproducibility of the result of the subjective speech quality assessment through crowdsourcing using our implementation. Finally, we quantify the impact of parts of the system designed to improve the reliability: environmental tests, gold and trapping questions, rating patterns, and a headset usage test.

For agents

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

get_harvested_code_for_paper("2005.08138")
get_code_for_paper("2005.08138")
have("2005.08138")

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

curl https://syntology.ai/api/ran/2005.08138.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.08138.svg)](https://syntology.ai/paper/2005.08138)

Connect an agent — have() is free.