SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.01227 · 2022

Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 5 have no contract verdict; 0 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/2204.01227.json · badge: /api/ran/2204.01227.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
wyu-du/gp-vae canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
construct_input_for_batch Ran
ran on a synthesized input
wyu-du/gp-vae/models/t5/utils.py
code served (permissive licence) · get_code("d15ef235457ba9f5")
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 tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

class SimpleTokenizer:
    """Minimal tokenizer stand-in"""
    def __call__(self, text):
        return {"input_ids": torch.tensor([1, 2, 3])}
    
    def encode(self, text):
        return [1, 2, 3]
    
    def decode(self, ids):
        return "decoded text"

# Create a minimal batch dictionary matching what the function expects
batch = {
    'source': ['hello world', 'foo bar'],
    'target': ['world hello', 'bar foo'],
    'id': [0, 1]
}

# Create a minimal tokenizer
tokenizer = SimpleTokenizer()

# Create minimal args (the function doesn't actually use it, but it's a parameter)
args = {}

ARGS = {
    'tokenizer': tokenizer,
    'batch': batch,
    'args': args
}
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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
evaluate Ran
ran on a synthesized input
wyu-du/gp-vae/models/pg/training.py
code served (permissive licence) · get_code("f145cea183a02846")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# Define a minimal model that satisfies the function's usage
class MinimalVAE(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def forward(self, batch, test=False):
        # The function calls model(batch, test=True) and expects (nll, kld) tuple
        # Both should be scalars wrapped in tensors with .item() method
        nll = torch.tensor(0.5)
        kld = torch.tensor(0.3)
        return nll, kld

# Create model instance
model = MinimalVAE()

# Create a minimal batch iterator
# Each batch should be something the model can accept
class MinimalBatch:
    def __init__(self):
        self.data = torch.randn(2, 4)

val_iter = [MinimalBatch() for _ in range(3)]

# Create a minimal txtfield (only needs to exist, not used in function body)
class MinimalTextField:
    pass

txtfield = MinimalTextField()

# Create minimal args (only needs to exist, not used in function body)
args = {}

ARGS = {
    "model": model,
    "val_iter": val_iter,
    "txtfield": txtfield,
    "args": args
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
kl_anneal_weight Ran
ran on a synthesized input
wyu-du/gp-vae/models/pg/utils.py
code served (permissive licence) · get_code("0fa184670e96ee9b")
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 1, dtype family float, shape (1,) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

class Args:
    def __init__(self):
        self.kw = 0.5
        self.x0 = 10
        self.using_cuda = False

ARGS = {
    "step": 5,
    "args": Args()
}
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 1, dtype family float, shape (1,) — shape (1,) 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
make_batch_inputs Ran
ran on a synthesized input
wyu-du/gp-vae/models/t5/utils.py
code served (permissive licence) · get_code("54cd3d08a29ec251")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

class MockTokenizer:
    def __call__(self, texts, padding=True, return_tensors='pt'):
        """Mock tokenizer that returns a dict of tensors"""
        # Create mock token IDs and attention masks
        batch_size = len(texts)
        max_length = max(len(t.split()) for t in texts) + 1 if texts else 5
        
        input_ids = torch.randint(0, 1000, (batch_size, max_length))
        attention_mask = torch.ones((batch_size, max_length))
        
        return {
            'input_ids': input_ids,
            'attention_mask': attention_mask,
            'token_type_ids': torch.zeros((batch_size, max_length), dtype=torch.long)
        }

class MockArgs:
    """Mock args object"""
    def __init__(self):
        self.max_length = 128
        self.model_name = "mock-model"

# Create a sample batch
batch = {
    'source': ['hello world', 'foo bar'],
    'target': ['goodbye world', 'baz qux'],
    'id': [0, 1]
}

tokenizer = MockTokenizer()
args = MockArgs()

ARGS = {
    'batch': batch,
    'tokenizer': tokenizer,
    'args': args,
    'device': 'cpu'
}
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 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
parse_data Ran
ran on a synthesized input
wyu-du/gp-vae/models/t5/utils.py
code served (permissive licence) · get_code("5a0e39bae457be59")
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 DataFrame. 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 pandas as pd
import tempfile
import os

# Create a temporary TSV file with sample data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, 'test.tsv')

with open(temp_file, 'w') as f:
    f.write("hello world\tbonjour monde\n")
    f.write("good morning\tbon matin\n")
    f.write("how are you\tcomment allez-vous\n")

ARGS = {
    'in_file': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 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.

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

Generating high quality texts with high diversity is important for many NLG applications, but current methods mostly focus on building deterministic models to generate higher quality texts and do not provide many options for promoting diversity. In this work, we present a novel latent structured variable model to generate high quality texts by enriching contextual representation learning of encoder-decoder models. Specifically, we introduce a stochastic function to map deterministic encoder hidden states into random context variables. The proposed stochastic function is sampled from a Gaussian process prior to (1) provide infinite number of joint Gaussian distributions of random context variables (diversity-promoting) and (2) explicitly model dependency between context variables (accurate-encoding). To address the learning challenge of Gaussian processes, we propose an efficient variational inference approach to approximate the posterior distribution of random context variables. We evaluate our method in two typical text generation tasks: paraphrase generation and text style transfer. Experimental results on benchmark datasets demonstrate that our method improves the generation quality and diversity compared with other baselines.

For agents

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

get_harvested_code_for_paper("2204.01227")
get_code_for_paper("2204.01227")
have("2204.01227")

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

curl https://syntology.ai/api/ran/2204.01227.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.01227.svg)](https://syntology.ai/paper/2204.01227)

Connect an agent — have() is free.