SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.11270 · 2018

Weakly-Supervised Hierarchical Text Classification

arXiv · PDF · Open in the Atlas

Code that ran

4 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 3 have no contract verdict; 1 failure of our instrument; 1 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/1812.11270.json · badge: /api/ran/1812.11270.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
yumeng5/WeSHClass canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
IndexLayer Ran
ran on a synthesized input
yumeng5/WeSHClass/models.py
code served (permissive licence) · get_code("c559fa2553f59cc4")
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 Lambda. 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 numpy as np

idx = 2

ARGS = {
    "idx": idx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Lambda — a Lambda output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Lambda 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
LSTMLanguageModel Ran
ran on a synthesized input
yumeng5/WeSHClass/models.py
code served (permissive licence) · get_code("6011888ac4b73a9f")
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 Functional. 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 numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Define parameters for the LSTM Language Model
input_shape = 10  # sequence length
word_embedding_dim = 8  # embedding dimension
vocab_sz = 100  # vocabulary size
hidden_dim = 16  # LSTM hidden dimension

# Create a small embedding matrix
# Shape: (vocab_size, embedding_dim)
embedding_matrix = np.random.randn(vocab_sz, word_embedding_dim).astype('float32')

# Construct ARGS dictionary
ARGS = {
    'input_shape': input_shape,
    'word_embedding_dim': word_embedding_dim,
    'vocab_sz': vocab_sz,
    'hidden_dim': hidden_dim,
    'embedding_matrix': embedding_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
clean_str Ran
ran on a synthesized input
yumeng5/WeSHClass/load_data.py
code served (permissive licence) · get_code("c7ce016cdc8da261")
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

def clean_str(string):
    string = re.sub('[^A-Za-z0-9(),.!?\\"\\\'-]', ' ', string)
    string = re.sub("\\'s", " 's", string)
    string = re.sub('\\"', ' " ', string)
    string = re.sub("\\'ve", " 've", string)
    string = re.sub("n\\'t", " n't", string)
    string = re.sub("\\'m", " 'm", string)
    string = re.sub("\\'re", " 're", string)
    string = re.sub("\\'d", " 'd", string)
    string = re.sub("\\'ll", " 'll", string)
    string = re.sub(',', ' , ', string)
    string = re.sub('\\.', ' . ', string)
    string = re.sub('!', ' ! ', string)
    string = re.sub('\\$', ' $ ', string)
    string = re.sub('\\(', ' \\( ', string)
    string = re.sub('\\)', ' \\) ', string)
    string = re.sub('\\?', ' \\? ', string)
    string = re.sub('\\s{2,}', ' ', string)
    return string.strip().lower()

ARGS = {
    "string": "Hello world! I'm testing this function's behavior with some special chars (like @#$). It's great, isn't it?"
}
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
preprocess_doc Ran
ran; our contract draft was wrong, not the code
yumeng5/WeSHClass/load_data.py
code served (permissive licence) · get_code("6b0a5dbed36c8258")
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 list, 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 re

def clean_str(string):
    string = re.sub('[^A-Za-z0-9(),.!?\\"\\\'-]', ' ', string)
    string = re.sub("\\'s", " 's", string)
    string = re.sub('\\"', ' " ', string)
    string = re.sub("\\'ve", " 've", string)
    string = re.sub("n\\'t", " n't", string)
    string = re.sub("\\'m", " 'm", string)
    string = re.sub("\\'re", " 're", string)
    string = re.sub("\\'d", " 'd", string)
    string = re.sub("\\'ll", " 'll", string)
    string = re.sub(',', ' , ', string)
    string = re.sub('\\.', ' . ', string)
    string = re.sub('!', ' ! ', string)
    string = re.sub('\\$', ' $ ', string)
    string = re.sub('\\(', ' \\( ', string)
    string = re.sub('\\)', ' \\) ', string)
    string = re.sub('\\?', ' \\? ', string)
    string = re.sub('\\s{2,}', ' ', string)
    return string.strip().lower()

def preprocess_doc(data):
    data = [s.strip() for s in data]
    data = [clean_str(s) for s in data]
    return data

# Construct test data
test_data = [
    "  Hello, world! How are you?  ",
    "  This is a test. I'm happy!  ",
    "  What's happening here (really)?  "
]

ARGS = {
    "data": test_data
}
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 list, ndim 1, dtype family float — a list 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
train_lstm Not yet run
unverified (harvested, no recorded run)
yumeng5/WeSHClass/utils.py
code served (permissive licence) · get_code("0fbb7309117d3b2c")
How it ran

no invocation recorded.

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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
preprocess_doc 1 other paper
1 later
2307.01878 (2023-07)
KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation

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

Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due to their expressive power and minimum requirement for feature engineering. However, applying deep neural networks for hierarchical text classification remains challenging, because they heavily rely on a large amount of training data and meanwhile cannot easily determine appropriate levels of documents in the hierarchical setting. In this paper, we propose a weakly-supervised neural method for hierarchical text classification. Our method does not require a large amount of training data but requires only easy-to-provide weak supervision signals such as a few class-related documents or keywords. Our method effectively leverages such weak supervision signals to generate pseudo documents for model pre-training, and then performs self-training on real unlabeled data to iteratively refine the model. During the training process, our model features a hierarchical neural structure, which mimics the given hierarchy and is capable of determining the proper levels for documents with a blocking mechanism. Experiments on three datasets from different domains demonstrate the efficacy of our method compared with a comprehensive set of baselines.

For agents

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

get_harvested_code_for_paper("1812.11270")
get_code_for_paper("1812.11270")
have("1812.11270")

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

curl https://syntology.ai/api/ran/1812.11270.json

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

[![Syntology run record](https://syntology.ai/api/ran/1812.11270.svg)](https://syntology.ai/paper/1812.11270)

Connect an agent — have() is free.