SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.26595 · 2026

PQuantML: A Tool for End-to-End Hardware-Aware Model Compression

Maurizio Pierini, Vladimir Loncar, Mia Liu, Chang Sun, Michael Kagan, Dimitrios Danopoulos, Enrico Lupi, Roope Niemi, Anastasiia Petrovych, Arghya Das, Marlon Helbing, Sebastian Dittmeier

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 2 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/2603.26595.json · badge: /api/ran/2603.26595.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
cern-nextgen/PQuantML canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
hard_sigmoid Ran
ran, honoured the contract we drafted
cern-nextgen/PQuantML/src/pquant/core/keras/activations.py
code served (permissive licence) · get_code("b13bc14536964bbd")
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 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
from keras import ops

torch.manual_seed(0)

# Create a small tensor to pass to hard_sigmoid
# The function expects a tensor-like input and applies element-wise operations
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
keras, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
hard_tanh Ran
ran, honoured the contract we drafted
cern-nextgen/PQuantML/src/pquant/core/keras/activations.py
code served (permissive licence) · get_code("24f4ff77227df47d")
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 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
from keras import ops as keras_ops

torch.manual_seed(0)

# Create a small tensor input for hard_tanh
# The function expects a tensor-like object that works with keras.ops operations
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
keras, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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_default_config Not yet run
unverified (harvested, no recorded run)
cern-nextgen/PQuantML/src/pquant/core/utils.py
code served (permissive licence) · get_code("13bb3cd054b6e480")
How it ran

no invocation recorded.

get_pruning_config Not yet run
unverified (harvested, no recorded run)
cern-nextgen/PQuantML/src/pquant/core/utils.py
code served (permissive licence) · get_code("e47ad3748cde158d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to environments with strict latency constraints, PQuantML simplifies training of compressed models by providing a unified interface to apply pruning and quantization, either jointly or individually. The library implements multiple pruning methods with different granularities, as well as fixed-point quantization with support for High-Granularity Quantization. We evaluate PQuantML on representative tasks such as the jet substructure classification, socalled jet tagging, an on-edge problem related to real-time LHC data processing. Using various pruning methods with fixed-point quantization, PQuantML achieves substantial parameter and bit-width reductions while maintaining accuracy. The resulting compression is further compared against existing tools, such as QKeras and HGQ.

For agents

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

get_harvested_code_for_paper("2603.26595")
get_code_for_paper("2603.26595")
have("2603.26595")

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

curl https://syntology.ai/api/ran/2603.26595.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.26595.svg)](https://syntology.ai/paper/2603.26595)

Connect an agent — have() is free.