Code that ran
2 of 2 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 2 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
- 2 ran with no instrument failure
0 honoured the contract we drafted, 0 violated it, 2 have no contract verdict
- 0 ran where Syntology's instrument failed
failures of Syntology's instrument, not of the code: 0 where our contract draft was wrong, 0 where the contract check could not run
- 0 have no recorded run
- 0 of those that ran constructed an object rather than computing a result
an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result
- 0 are pointer only: the body is not served under this paper's link
"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/2002.08679.json · badge: /api/ran/2002.08679.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.
| Repository | Role | Ran |
|---|
| openvinotoolkit/nncf |
canonical (classifier label) classifier basis: census |
2 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|
| deprecated |
Ran ran on a synthesized input |
openvinotoolkit/nncf/src/nncf/common/deprecation.py code served (permissive licence) · get_code("aad730edbb0a232f") How it ranRan 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 types
import warnings
from functools import wraps
from typing import Any, Callable, TypeVar, cast
torch = None
try:
import torch
except ImportError:
pass
TObj = TypeVar('TObj')
def warning_deprecated(msg: str) -> None:
"""
Display a warning message indicating that a certain functionality is deprecated.
:param msg: The warning message to display.
"""
warnings.warn(msg, FutureWarning, stacklevel=2)
def _generate_deprecation_message(name: str, text: str | None, start_version: str | None, end_version: str | None) -> str:
"""
Generate a deprecation message for a given name, with optional start and end versions.
:param name: The name of the deprecated feature.
:param text: Additional text to include in the deprecation message.
:param start_version: The version from which the feature is deprecated.
:param end_version: The version in which the feature will be removed.
:return: The deprecation message.
"""
msg = f"Usage of {name} is deprecated {(f'starting from NNCF v{start_version} ' if start_version else '')}and will be removed in {(f'NNCF v{end_version}.' if end_version else 'a future NNCF version.')}"
if text:
return '\n'.join([msg, text])
return msg
def deprecated(msg: str | None=None, start_version: str | None=None, end_version: str | None=None) -> Callable[[TObj], TObj]:
"""
Decorator to mark a function or class as deprecated.
:param msg: Message to provide additional information about the deprecation.
:param start_version: Start version from which the function or class is deprecated.
:param end_version: End version until which the function or class is deprecated.
:return: The decorator function.
"""
def decorator(obj: TObj) -> TObj:
if isinstance(obj, types.FunctionType):
@wraps(obj)
def wrapper(*args: Any, **kwargs: Any) -> Any:
name = f"function '{obj.__module__}.{obj.__name__}'"
text = _generate_deprecation_message(name, msg, start_version, end_version)
warning_deprecated(text)
return obj(*args, **kwargs)
return cast(TObj, wrapper)
if isinstance(obj, type):
original_init = obj.__init__
@wraps(original_init)
def wrapped_init(*args: Any, **kwargs: Any) -> Any:
name = f"class '{obj.__module__}.{obj.__name__}'"
text = _generate_deprecation_message(name, msg, start_version, end_version)
warning_deprecated(text)
return original_init(*args, **kwargs)
obj.__init__ = wrapped_init
return cast(TObj, obj)
err_msg = 'The @deprecated decorator can only be used on functions or classes.'
raise TypeError(err_msg)
return decorator
# Test function to decorate
def sample_function():
return "test result"
# Test class to decorate
class SampleClass:
def __init__(self):
self.value = 42
ARGS = {
'msg': 'This feature is no longer supported, please use new_feature instead.',
'start_version': '1.0.0',
'end_version': '2.0.0'
}
- 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
|
| matches_any |
Ran ran on a synthesized input |
openvinotoolkit/nncf/src/nncf/common/scopes.py code served (permissive licence) · get_code("a929dd7a8ba33da0") How it ranRan 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.
import re
from typing import Iterable
def matches_any(tested_str: str, strs_to_match_to: Iterable[str] | str | None) -> bool:
"""
Return True if tested_str matches at least one element in strs_to_match_to.
:param tested_str: One of the supported entity types to be matched - currently possible to pass either
NNCFNodeName (to refer to the original model operations) or QuantizerId (to refer to specific quantizers).
:param strs_to_match_to: A list or set of strings specifying for the serializable_id. Entries of the strings
may be prefixed with `{re}` to enable regex matching.
:return: A boolean value specifying whether a tested_str should matches at least one element
in strs_to_match_to.
"""
if strs_to_match_to is None:
return False
str_list = [strs_to_match_to] if isinstance(strs_to_match_to, str) else strs_to_match_to
for item in str_list:
if '{re}' in item:
regex = item.replace('{re}', '')
if re.search(regex, tested_str):
return True
elif tested_str == item:
return True
return False
ARGS = {
"tested_str": "quantizer_0",
"strs_to_match_to": [
"quantizer_0",
"{re}quant.*",
"other_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 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
|
Also present in other papers' code
Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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 2026-11-21.
Repositories linked to this paper
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Abstract
In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF). It leverages recent advances of various network compression methods and implements some of them, such as sparsity, quantization, and binarization. These methods allow getting more hardware-friendly models which can be efficiently run on general-purpose hardware computation units (CPU, GPU) or special Deep Learning accelerators. We show that the developed methods can be successfully applied to a wide range of models to accelerate the inference time while keeping the original accuracy. The framework can be used within the training samples, which are supplied with it, or as a standalone package that can be seamlessly integrated into the existing training code with minimal adaptations. Currently, a PyTorch version of NNCF is available as a part of OpenVINO Training Extensions at https://github.com/openvinotoolkit/nncf.
For agents
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2002.08679")
get_code_for_paper("2002.08679")
have("2002.08679")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2002.08679.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2002.08679)
Connect an agent — have() is free.