SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.03243 · ICLR · 2022

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Jiawei Han, Chenyan Xiong, Yu Meng, Payal Bajaj, Saurabh Tiwary, Paul Bennett, Xia Song, -Champaign

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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 1 has no contract verdict; 3 failures of our instrument; 4 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2204.03243.json · badge: /api/ran/2204.03243.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
microsoft/amos canonical (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
to_list Ran
ran; our contract draft was wrong, not the code
microsoft/amos/huggingface/run_squad.py
pointer only (licence: MIT); the stored copy get_code serves, from AI-secure/InfoBERT, is pointer only (licence: NONE) · get_code("9df40357afea56cc")
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 AI-secure/InfoBERT, 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.

acc_and_f1 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
microsoft/amos/huggingface/utils_for_glue.py
pointer only (licence: MIT); the stored copy get_code serves, from danrsc/bert_brain_neurips_2019, is pointer only (licence: NONE) · get_code("cac113ca87b9d9f3")
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 danrsc/bert_brain_neurips_2019, 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.

grad_multiply Ran
ran on a synthesized input
microsoft/amos/fairseq/fairseq/models/amos/model.py
code served (permissive licence) · get_code("4d8fd9c4df4cdbf8")
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 a small tensor to pass to grad_multiply
x = torch.randn(2, 4, requires_grad=True)

# Create a lambda (gradient multiplier) value
lambd = -1.0

# Define ARGS dict with all parameters
ARGS = {
    'x': x,
    'lambd': lambd
}
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
relative_position_bucket Ran
ran; our contract draft was wrong, not the code
microsoft/amos/huggingface/amos/modeling_amos.py
code served (permissive licence) · get_code("56a2f49e4e3b9f21")
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 int, 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 math

torch.manual_seed(0)

# Create a small tensor for relative_position
# The function expects a tensor of relative positions (can be any shape)
relative_position = torch.tensor([[-5, -2, 0, 3], [8, 15, 50, 120]], dtype=torch.long)

# Standard parameters for the function
num_buckets = 32
max_distance = 128

ARGS = {
    "relative_position": relative_position,
    "num_buckets": num_buckets,
    "max_distance": max_distance,
}
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 int, 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_optimizer_grouped_parameters Not yet run
unverified (harvested, no recorded run)
microsoft/amos/huggingface/run_glue.py
code served (permissive licence) · get_code("12cd41e0ee10b80e")
How it ran

no invocation recorded.

get_optimizer_grouped_parameters Not yet run
unverified (harvested, no recorded run)
microsoft/amos/huggingface/run_squad.py
code served (permissive licence) · get_code("8da182308e4e4fd1")
How it ran

no invocation recorded.

glue_convert_examples_to_features Not yet run
unverified (harvested, no recorded run)
microsoft/amos/huggingface/utils_for_glue.py
code served (permissive licence) · get_code("0c9432834249738e")
How it ran

no invocation recorded.

simple_accuracy Not yet run
unverified (harvested, no recorded run)
microsoft/amos/huggingface/utils_for_glue.py
code served (permissive licence) · get_code("3c241ecfe3749a6d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
simple_accuracy 59 other papers
42 dated earlier, 2 the same month, 15 later
1506.05865 (2015-06)
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
1509.01626 (2015-09)
Character-level Convolutional Networks for Text Classification *
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 56 more not named here
to_list 41 other papers
29 dated earlier, 12 later
1902.01718 (2019-02)
End-to-End Open-Domain Question Answering with BERTserini
1910.06188 (2019-10)
Q8BERT: Quantized 8Bit BERT
1911.02984 (2019-11)
The TechQA Dataset
and 38 more not named here
acc_and_f1 22 other papers
12 dated earlier, 1 the same month, 9 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1905.12866 (2019-05)
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
and 19 more not named here
relative_position_bucket 2 other papers
2 later
2208.00108 (2022-08)
Some Practice for Improving the Search Results of E-commerce
2406.12527 (2024-06)
FuseGen: PLM Fusion for Data-generation based Zero-shot Learning

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

We present a new framework AMOS that pretrains text encoders with an Adversarial learning curriculum via a Mixture Of Signals from multiple auxiliary generators. Following ELECTRA-style pretraining, the main encoder is trained as a discriminator to detect replaced tokens generated by auxiliary masked language models (MLMs). Different from ELECTRA which trains one MLM as the generator, we jointly train multiple MLMs of different sizes to provide training signals at various levels of difficulty. To push the discriminator to learn better with challenging replaced tokens, we learn mixture weights over the auxiliary MLMs' outputs to maximize the discriminator loss by backpropagating the gradient from the discriminator via Gumbel-Softmax. For better pretraining efficiency, we propose a way to assemble multiple MLMs into one unified auxiliary model. AMOS outperforms ELECTRA and recent state-of-the-art pretrained models by about 1 point on the GLUE benchmark for BERT base-sized models.

For agents

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

get_harvested_code_for_paper("2204.03243")
get_code_for_paper("2204.03243")
have("2204.03243")

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

curl https://syntology.ai/api/ran/2204.03243.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.03243.svg)](https://syntology.ai/paper/2204.03243)

Connect an agent — have() is free.