SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.07195 · 2019

ARAML: A Stable Adversarial Training Framework for Text Generation

arXiv · PDF · Open in the Atlas

Code that ran

None of the 4 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (4 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/1908.07195.json · badge: /api/ran/1908.07195.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
kepei1106/ARAML canonical (classifier label)
classifier basis: census
0 ran · 4 no recorded run
FunctionStatusWhere it lives
highway Not yet run
unverified (harvested, no recorded run)
kepei1106/ARAML/src/coco_emnlp/araml_rewarder.py
code served (permissive licence) · get_code("a3124578eae0196c")
How it ran

no invocation recorded.

linear Not yet run
unverified (harvested, no recorded run)
kepei1106/ARAML/src/coco_emnlp/araml_rewarder.py
code served (permissive licence) · get_code("0a26e6ea99bbd1eb")
How it ran

no invocation recorded.

output_projection_layer Not yet run
unverified (harvested, no recorded run)
kepei1106/ARAML/src/coco_emnlp/lm/my_output_projection.py
code served (permissive licence) · get_code("35d59903533d24ac")
How it ran

no invocation recorded.

sequence_loss Not yet run
unverified (harvested, no recorded run)
kepei1106/ARAML/src/coco_emnlp/lm/my_loss.py
code served (permissive licence) · get_code("59c960268be04f6d")
How it ran

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, 0 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
linear 2 other papers
2 dated earlier
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.05334 (2018-10)
IndoSum: A New Benchmark Dataset for Indonesian Text Summarization
highway 1 other paper
1 dated earlier
1810.05334 (2018-10)
IndoSum: A New Benchmark Dataset for Indonesian Text 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we propose a novel framework called Adversarial Reward Augmented Maximum Likelihood (ARAML). During adversarial training, the discriminator assigns rewards to samples which are acquired from a stationary distribution near the data rather than the generator's distribution. The generator is optimized with maximum likelihood estimation augmented by the discriminator's rewards instead of policy gradient. Experiments show that our model can outperform state-of-the-art text GANs with a more stable training process.

For agents

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

get_harvested_code_for_paper("1908.07195")
get_code_for_paper("1908.07195")
have("1908.07195")

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

curl https://syntology.ai/api/ran/1908.07195.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.07195.svg)](https://syntology.ai/paper/1908.07195)

Connect an agent — have() is free.