SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.12002 · ACL · 2021

Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization

Tuo Zhao, Chen Liang, Haoming Jiang, Minshuo Chen, Weizhu Chen, Xiaodong Liu, Simiao Zuo, Pengcheng He

arXiv · PDF · Open in the Atlas

Code that ran

15 of 15 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 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/2105.12002.json · badge: /api/ran/2105.12002.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
cliang1453/super-structured-lottery-tickets canonical (classifier label)
classifier basis: census
15 ran · 0 no recorded run
FunctionStatusWhere it lives
bertgelu Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/module/common.py
pointer only (licence: MIT) · get_code("1294e1fa682e2b8c")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

build_data_single Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/extractor.py
pointer only (licence: MIT) · get_code("a034fa2c801b129f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

determine_masking_sequence Ran
ran, honoured the contract we drafted
cliang1453/super-structured-lottery-tickets/masking.py
pointer only (licence: MIT) · get_code("3764f415f19251f4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

encode_pieces Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/data_utils/xlnet_utils.py
pointer only (licence: MIT) · get_code("0de7059b7a331eb0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

gelu Ran
ran, honoured the contract we drafted
cliang1453/super-structured-lottery-tickets/module/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from lonePatient/BERT-SDA, is pointer only (licence: NONE) · get_code("211753ba29188d4e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

gelu_new Ran
ran, honoured the contract we drafted
cliang1453/super-structured-lottery-tickets/module/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from lonePatient/BERT-SDA, is pointer only (licence: NONE) · get_code("77601724cad03f95")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

linear Ran
ran, honoured the contract we drafted
cliang1453/super-structured-lottery-tickets/module/common.py
pointer only (licence: MIT); the stored copy get_code serves, from MrHuff/Sumo-Net, is pointer only (licence: NONE) · get_code("691b566282a42d88")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from MrHuff/Sumo-Net, and GitHub detected no licence in that repository when it was checked. 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_data Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/extractor.py
pointer only (licence: MIT) · get_code("273950f7bcb961ae")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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 Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/module/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from tanmay1618/text_to_sql_bert, is pointer only (licence: NONE) · get_code("0c145728a35789fa")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

preprocess_text Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/data_utils/xlnet_utils.py
pointer only (licence: MIT) · get_code("b19697c998adb1ea")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

printable_text Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/data_utils/xlnet_utils.py
pointer only (licence: MIT) · get_code("0e5615f8994003cf")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

swish Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/module/common.py
pointer only (licence: MIT) · get_code("47cf8803722c3336")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

warmup_linear_xdl Ran
ran, honoured the contract we drafted
cliang1453/super-structured-lottery-tickets/module/bert_optim.py
code served (permissive licence) · get_code("dea985d5f4e928e8")
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

torch.manual_seed(0)

# The function takes two parameters:
# - x: a float value between 0 and 1 (representing training progress)
# - warmup: a float value representing the warmup fraction (default 0.002)

# Looking at the function body:
# - x is compared with warmup (< operator)
# - x and warmup are used in arithmetic operations (division, subtraction)
# - The function returns float values

# Create valid arguments
x_value = 0.5  # A float representing progress through training (between 0 and 1)
warmup_value = 0.1  # A float representing the warmup fraction

ARGS = {
    "x": x_value,
    "warmup": warmup_value,
}
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 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
what_to_mask Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/masking.py
pointer only (licence: MIT) · get_code("fca2c0b9e35c90c3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

what_to_threshold Ran
ran; our contract draft was wrong, not the code
cliang1453/super-structured-lottery-tickets/masking.py
pointer only (licence: MIT) · get_code("1218c6ee351ccc7f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, cliang1453/super-structured-lottery-tickets, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 1 the same month, 6 later) and 5 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
gelu 198 other papers
73 dated earlier, 3 the same month, 118 later, 4 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
printable_text 33 other papers
19 dated earlier, 13 later, 1 same year, order not determinable
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.04085 (2019-01)
Passage Re-ranking with BERT
and 30 more not named here
gelu_new 23 other papers
13 dated earlier, 10 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
1911.03631 (2019-11)
Hierarchical Graph Network for Multi-hop Question Answering
and 20 more not named here
load_tf_weights_in_bert 19 other papers
11 dated earlier, 8 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1902.01069 (2019-02)
A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
and 16 more not named here
linear 6 other papers
4 dated earlier, 2 later · 1 only as an assembly brick
1803.06585 (2018-03)
Learning Long Term Dependencies via Fourier Recurrent Units
1901.11504 (2019-01)
Multi-Task Deep Neural Networks for Natural Language Understanding
2001.01565 (2020-01)
Stance Detection Benchmark: How Robust Is Your Stance Detection?
and 3 more not named here
swish 2 other papers
2 dated earlier
2001.01565 (2020-01)
Stance Detection Benchmark: How Robust Is Your Stance Detection?
2104.04886 (2021-04)
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
warmup_linear_xdl 2 other papers
1 dated earlier, 1 later
2001.01565 (2020-01)
Stance Detection Benchmark: How Robust Is Your Stance Detection?
2202.02664 (2022-02)
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models
bertgelu 1 other paper
1 dated earlier
2104.04886 (2021-04)
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
encode_pieces 1 other paper
1 dated earlier
2004.13922 (2020-04)
Revisiting Pre-trained Models for Chinese Natural Language Processing
preprocess_text 1 other paper
1 dated earlier
2004.13922 (2020-04)
Revisiting Pre-trained Models for Chinese Natural Language Processing

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 Lottery Ticket Hypothesis suggests that an over-parametrized network consists of "lottery tickets", and training a certain collection of them (i.e., a subnetwork) can match the performance of the full model. In this paper, we study such a collection of tickets, which is referred to as "winning tickets", in extremely over-parametrized models, e.g., pre-trained language models. We observe that at certain compression ratios, the generalization performance of the winning tickets can not only match but also exceed that of the full model. In particular, we observe a phase transition phenomenon: As the compression ratio increases, generalization performance of the winning tickets first improves then deteriorates after a certain threshold. We refer to the tickets on the threshold as "super tickets". We further show that the phase transition is task and model dependent -as the model size becomes larger and the training data set becomes smaller, the transition becomes more pronounced. Our experiments on the GLUE benchmark show that the super tickets improve single task fine-tuning by 0.9 points on BERT-base and 1.0 points on BERT-large, in terms of task-average score. We also demonstrate that adaptively sharing the super tickets across tasks benefits multi-task learning 1 .

For agents

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

get_harvested_code_for_paper("2105.12002")
get_code_for_paper("2105.12002")
have("2105.12002")

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

curl https://syntology.ai/api/ran/2105.12002.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.12002.svg)](https://syntology.ai/paper/2105.12002)

Connect an agent — have() is free.