SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.02480 · 2019

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 0 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/1909.02480.json · badge: /api/ran/1909.02480.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
XuezheMax/flowseq canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_bleu Ran
ran, honoured the contract we drafted
XuezheMax/flowseq/experiments/translate.py
code served (permissive licence) · get_code("6890088b59086e6e")
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 os
import tempfile
import shutil

# Create temporary directories and files for testing
temp_dir = tempfile.mkdtemp()
result_path = tempfile.mkdtemp()

# Create a mock reference file
fref_path = os.path.join(temp_dir, 'reference.txt')
with open(fref_path, 'w') as f:
    f.write('this is a test reference\n')
    f.write('another reference line\n')

# Create a mock translation/format file
fmt_path = os.path.join(temp_dir, 'translation.txt')
with open(fmt_path, 'w') as f:
    f.write('this is a test reference\n')
    f.write('another reference line\n')

# Create a mock multi-bleu.perl script that outputs a valid BLEU score
scripts_dir = os.path.join(temp_dir, 'scripts')
os.makedirs(scripts_dir, exist_ok=True)
script_path = os.path.join(scripts_dir, 'multi-bleu.perl')
with open(script_path, 'w') as f:
    f.write('#!/usr/bin/perl\n')
    f.write('print "BLEU = 45.32, 58.2/48.3/39.1/30.2 (BP=0.982, ratio=0.982, hyp_len=28, ref_len=29)\\n";\n')

os.chmod(script_path, 0o755)

# Patch the current_path to point to our temp directory
import sys
import types

# Create a mock module to override the current_path
mock_module = types.ModuleType('mock_calc_bleu')
mock_module.current_path = temp_dir

ARGS = {
    'fref': fref_path,
    'fmt': fmt_path,
    'result_path': result_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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 sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased efficiency through parallel processing on hardware such as GPUs. However, directly modeling the joint distribution of all tokens simultaneously is challenging, and even with increasingly complex model structures accuracy lags significantly behind autoregressive models. In this paper, we propose a simple, efficient, and effective model for non-autoregressive sequence generation using latent variable models. Specifically, we turn to generative flow, an elegant technique to model complex distributions using neural networks, and design several layers of flow tailored for modeling the conditional density of sequential latent variables. We evaluate this model on three neural machine translation (NMT) benchmark datasets, achieving comparable performance with state-of-the-art non-autoregressive NMT models and almost constant decoding time w.r.t the sequence length.

For agents

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

get_harvested_code_for_paper("1909.02480")
get_code_for_paper("1909.02480")
have("1909.02480")

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

curl https://syntology.ai/api/ran/1909.02480.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.02480.svg)](https://syntology.ai/paper/1909.02480)

Connect an agent — have() is free.