SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.07463 · 2020

Parameter-Efficient Transfer Learning with Diff Pruning

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 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.

"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/2012.07463.json · badge: /api/ran/2012.07463.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
dguo98/DiffPruning canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
FunctionStatusWhere it lives
concrete_stretched Ran
ran, violated the contract we drafted
dguo98/DiffPruning/examples/run_glue_diffpruning.py
code served (permissive licence) · get_code("60724158ace4ad5f")
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) and returned tuple, ndim 3, 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 torch

torch.manual_seed(0)

# alpha is used with torch.zeros_like, so it must be a tensor
# The function performs operations on it and returns tensors
alpha = torch.randn(2, 4)

# l and r are used in arithmetic operations (r - l) and for clamping
# They are scalar values (floats)
l = 0.0
r = 1.0

ARGS = {
    "alpha": alpha,
    "l": l,
    "r": r,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple 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
get_valid_metric Ran
ran, honoured the contract we drafted
dguo98/DiffPruning/examples/run_glue_diffpruning.py
code served (permissive licence) · get_code("3f11eba9ef6c2589")
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) 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function: it takes a result dict and a task string
# It accesses result[key] for various metric keys depending on the task
# The function returns a single metric value

# Create a result dict with all possible metrics that could be accessed
result = {
    'mcc': 0.85,
    'acc': 0.92,
    'f1': 0.88,
    'spearmanr': 0.91,
}

# Test with a valid task
task = 'cola'

ARGS = {
    'result': result,
    'task': task,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
mish Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from llyx97/sparse-and-robust-PLM
pointer only; the stored copy get_code serves, from llyx97/sparse-and-robust-PLM, is pointer only (licence: NONE) · get_code("060527bb34794b59")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from llyx97/sparse-and-robust-PLM
pointer only; the stored copy get_code serves, from llyx97/sparse-and-robust-PLM, is pointer only (licence: NONE) · get_code("0766f48ad6e01b56")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. 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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
mish 19 other papers
2 dated earlier, 17 later
2006.04884 (2020-06)
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2007.12223 (2020-07)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
2021.acl-long.390 (2021 (year only))
Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision
and 16 more not named here
load_tf_weights_in_bert 16 other papers
2 dated earlier, 14 later
2006.04884 (2020-06)
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2007.12223 (2020-07)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
2021.acl-long.390 (2021 (year only))
Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision
and 13 more not named here

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

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a simple approach to enable parameter-efficient transfer learning within the pretrain-finetune framework. This approach views finetuning as learning a task-specific diff vector that is applied on top of the pretrained parameter vector, which remains fixed and is shared across different tasks. The diff vector is adaptively pruned during training with a differentiable approximation to the L0-norm penalty to encourage sparsity. Diff pruning becomes parameter-efficient as the number of tasks increases, as it requires storing only the nonzero positions and weights of the diff vector for each task, while the cost of storing the shared pretrained model remains constant. It further does not require access to all tasks during training, which makes it attractive in settings where tasks arrive in stream or the set of tasks is unknown. We find that models finetuned with diff pruning can match the performance of fully finetuned baselines on the GLUE benchmark while only modifying 0.5% of the pretrained model's parameters per task.

For agents

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

get_harvested_code_for_paper("2012.07463")
get_code_for_paper("2012.07463")
have("2012.07463")

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

curl https://syntology.ai/api/ran/2012.07463.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.07463.svg)](https://syntology.ai/paper/2012.07463)

Connect an agent — have() is free.