SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.09522 · 2020

TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 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/2001.09522.json · badge: /api/ran/2001.09522.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
mickeysjm/taxoexpan canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
rearrange Ran
ran; our contract draft was wrong, not the code
mickeysjm/taxoexpan/test_fast.py
code served (permissive licence) · get_code("c298f48760d30d1c")
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 tuple. 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)

# Construct arguments for rearrange function
# The function expects:
# - energy_scores: a torch tensor that will be indexed with [correct, :] and [incorrect, :]
# - candidate_position_idx: a numpy array to check membership
# - parent_position_idx: a numpy array used as reference for membership check

# Create energy_scores as a 2D tensor (batch_size=5, features=4)
energy_scores = torch.randn(5, 4)

# Create candidate_position_idx as numpy array with some values
candidate_position_idx = np.array([0, 1, 2, 5, 7])

# Create parent_position_idx as numpy array - some values overlap with candidate
parent_position_idx = np.array([1, 2, 3, 4])

ARGS = {
    "energy_scores": energy_scores,
    "candidate_position_idx": candidate_position_idx,
    "parent_position_idx": parent_position_idx,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 — a tuple output has no array shape of its own; none is 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
encode_graph Not yet run
unverified (harvested, no recorded run)
mickeysjm/taxoexpan/test_fast.py
code served (permissive licence) · get_code("eef6e869d174ca4b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications. For example, online retailers (e.g., Amazon and eBay) use taxonomies for product recommendation, and web search engines (e.g., Google and Bing) leverage taxonomies to enhance query understanding. Enormous efforts have been made on constructing taxonomies either manually or semi-automatically. However, with the fast-growing volume of web content, existing taxonomies will become outdated and fail to capture emerging knowledge. Therefore, in many applications, dynamic expansions of an existing taxonomy are in great demand. In this paper, we study how to expand an existing taxonomy by adding a set of new concepts. We propose a novel self-supervised framework, named TaxoExpan, which automatically generates a set of <query concept, anchor concept> pairs from the existing taxonomy as training data. Using such self-supervision data, TaxoExpan learns a model to predict whether a query concept is the direct hyponym of an anchor concept. We develop two innovative techniques in TaxoExpan: (1) a position-enhanced graph neural network that encodes the local structure of an anchor concept in the existing taxonomy, and (2) a noise-robust training objective that enables the learned model to be insensitive to the label noise in the self-supervision data. Extensive experiments on three large-scale datasets from different domains demonstrate both the effectiveness and the efficiency of TaxoExpan for taxonomy expansion.

For agents

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

get_harvested_code_for_paper("2001.09522")
get_code_for_paper("2001.09522")
have("2001.09522")

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

curl https://syntology.ai/api/ran/2001.09522.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.09522.svg)](https://syntology.ai/paper/2001.09522)

Connect an agent — have() is free.