SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.10218 · 2022

GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator

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 2 have no contract verdict; 1 failure 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/2212.10218.json · badge: /api/ran/2212.10218.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
csjianyang/ganlm canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
clean Ran
ran; our contract draft was wrong, not the code
csjianyang/ganlm/evaluation/bs_pyrouge.py
code served (permissive licence) · get_code("bedeff473c33061f")
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 str. The image it ran in was not recorded. If your copy returns the same type 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 re

REMAP = {'-lrb-': '(', '-rrb-': ')', '-lcb-': '{', '-rcb-': '}', '-lsb-': '[', '-rsb-': ']', '``': '"', "''": '"'}

def clean(x):
    return re.sub("-lrb-|-rrb-|-lcb-|-rcb-|-lsb-|-rsb-|``|''", lambda m: REMAP.get(m.group()), x)

# The function takes a string x and applies regex substitution with REMAP dictionary
# We need to provide a string that contains some of the patterns that will be replaced

ARGS = {
    'x': "This is a test -lrb- with some -rrb- brackets and ``quotes'' and -lcb- braces -rcb- and -lsb- square -rsb- brackets"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
count_tokens Ran
ran on a synthesized input
csjianyang/ganlm/evaluation/cnn_dm.py
code served (permissive licence) · get_code("7d0f0d30d5c3027f")
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 dict. The image it ran in was not recorded. If your copy returns the same type 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)

# The function count_tokens takes a collection of tokens and counts their occurrences
# It iterates through tokens, checks if each token is in a counter dict, and increments counts
# The tokens parameter should be an iterable of hashable items (strings, ints, etc.)

tokens = ['apple', 'banana', 'apple', 'cherry', 'banana', 'apple']

ARGS = {
    'tokens': tokens
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
rouge_results_to_str Ran
ran on a synthesized input
csjianyang/ganlm/evaluation/cnn_dm.py
code served (permissive licence) · get_code("c19b75e22d2023fb")
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 str. The image it ran in was not recorded. If your copy returns the same type 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)

results_dict = {
    'rouge_1_f_score': 0.75,
    'rouge_2_f_score': 0.68,
    'rouge_l_f_score': 0.72,
    'rouge_1_recall': 0.80,
    'rouge_2_recall': 0.70,
    'rouge_l_recall': 0.75
}

ARGS = {
    'results_dict': results_dict
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
clean 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
1903.10318 (2019-03)
Fine-tune BERT for Extractive Summarization
1910.14142 (2019-10)
Discourse-Aware Neural Extractive Text Summarization
aaai_21432 (2022 (year only))
DIALOGLM: Pre-trained Model for Long Dialogue Understanding and Summarization
and 1 more not named here
count_tokens 1 other paper
1 same year, order not determinable
aaai_21432 (2022 (year only))
DIALOGLM: Pre-trained Model for Long Dialogue Understanding and Summarization
rouge_results_to_str 1 other paper
1 same year, order not determinable
aaai_21432 (2022 (year only))
DIALOGLM: Pre-trained Model for Long Dialogue Understanding and Summarization

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

Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model. Our model, named as GanLM, is trained with two pre-training objectives: replaced token detection and replaced token denoising. Specifically, given masked source sentences, the generator outputs the target distribution and the discriminator predicts whether the target sampled tokens from distribution are incorrect. The target sentence is replaced with misclassified tokens to construct noisy previous context, which is used to generate the gold sentence. In general, both tasks improve the ability of language understanding and generation by selectively using the denoising data. Extensive experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models (PLMs) and achieves state-of-the-art performance.

For agents

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

get_harvested_code_for_paper("2212.10218")
get_code_for_paper("2212.10218")
have("2212.10218")

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

curl https://syntology.ai/api/ran/2212.10218.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.10218.svg)](https://syntology.ai/paper/2212.10218)

Connect an agent — have() is free.