SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.01705 · 2025

Progressive Binarization with Semi-Structured Pruning for LLMs

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures of our instrument; 0 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/2502.01705.json · badge: /api/ran/2502.01705.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
xianglongyan/pbs2p canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
optimize_single_binary_mse Ran
ran; our contract draft was wrong, not the code
xianglongyan/pbs2p/pbs2p/spbo.py
code served (permissive licence) · get_code("ae4d2d4d13ace1cc")
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

torch.manual_seed(0)

# Create small tensors for the function
# weights: shape (batch_size, feature_dim)
# mask: shape (batch_size, feature_dim), boolean tensor

batch_size = 2
feature_dim = 4

weights = torch.randn(batch_size, feature_dim)
mask = torch.randint(0, 2, (batch_size, feature_dim)).bool()

# Ensure at least some True values in mask for meaningful computation
mask[0, 0] = True
mask[1, 1] = True

iterations = 15

ARGS = {
    "weights": weights,
    "mask": mask,
    "iterations": iterations,
}
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
optimize_two_binary_mse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xianglongyan/pbs2p/pbs2p/spbo.py
code served (permissive licence) · get_code("1dbd6d90eda1e2a6")
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 torch.nn as nn

torch.manual_seed(0)

# Create small tensors for the function
# weights: shape (batch_size, feature_size)
# mask: shape (batch_size, feature_size), boolean mask
batch_size = 2
feature_size = 4

weights = torch.randn(batch_size, feature_size)
mask = torch.ones(batch_size, feature_size, dtype=torch.bool)

# Set some mask values to False to create a proper mask
mask[0, 2] = False
mask[1, 3] = False

iterations = 3

ARGS = {
    'weights': weights,
    'mask': mask,
    'iterations': iterations,
}
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
residual_binarize Ran
ran; our contract draft was wrong, not the code
xianglongyan/pbs2p/pbs2p/spbo.py
code served (permissive licence) · get_code("e8195a8596672c94")
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
from torch import Tensor

torch.manual_seed(0)

# Create small tensors for testing
# weights: shape (batch=2, dim=4) - the weight matrix to binarize
weights = torch.randn(2, 4)

# mask: shape (batch=2, dim=4) - boolean mask indicating which values to consider
mask = torch.tensor([
    [True, True, False, True],
    [True, False, True, True]
], dtype=torch.bool)

# order: int parameter for number of iterations
order = 2

ARGS = {
    "weights": weights,
    "mask": mask,
    "order": order
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Large language models (LLMs) have achieved remarkable progress in natural language processing, but their high computational and memory costs hinder deployment on resource-constrained devices. Binarization represents the most extreme form of quantization, yet binarized models still contain redundancy that can be further removed. Pruning provides a natural way to eliminate such redundancy, but naïve combination with binarization often results in severe performance degradation. In this paper, we propose Progressive Binarization with Semi-Structured Pruning (PBS$^2$P), a novel post-training framework that seamlessly integrates binarization and semi-structured pruning. We first propose Stepwise semi-structured Pruning with Binarization Optimization (SPBO), which progressively introduces sparsity while optimizing binarization parameters to jointly reduce pruning and quantization error, yielding more stable and accurate compression. Additionally, we propose a Coarse-to-Fine Search (CFS) that first allocates pruning ratios and then refines element selection, further enhancing overall performance. Extensive experiments across multiple LLM families show that PBS$^2$P consistently outperforms state-of-the-art (SOTA) binary post-training quantization methods in both perplexity and downstream accuracy. The code and models will be available at https://github.com/XIANGLONGYAN/PBS2P.

For agents

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

get_harvested_code_for_paper("2502.01705")
get_code_for_paper("2502.01705")
have("2502.01705")

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

curl https://syntology.ai/api/ran/2502.01705.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.01705.svg)](https://syntology.ai/paper/2502.01705)

Connect an agent — have() is free.