SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.13207 · CVPR · 2022

Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework

Caiming Xiong, Ran Xu, Shu Zhang, Chetan Ramaiah

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure 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/2204.13207.json · badge: /api/ran/2204.13207.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
salesforce/hierarchicalcontrastivelearning marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
HMLC Ran
ran on a synthesized input · constructed an object; no result was computed
salesforce/hierarchicalcontrastivelearning/losses/losses.py
code served (permissive licence) · get_code("a7decda54bcc55a3")
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 an instance of its own class, HMLC: the run constructed the object and did not call it, so no result was computed. 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)

# Create tiny features tensor: [batch_size=2, n_views=2, feature_dim=4]
features = torch.randn(2, 2, 4)

# Create labels tensor: [batch_size=2, num_hierarchy_levels=3]
# Each row represents hierarchical labels for a sample
labels = torch.tensor([
    [1, 2, 3],
    [1, 2, 4]
], dtype=torch.long)

# Define a custom layer_penalty function (optional)
def custom_layer_penalty(value):
    return torch.pow(2.0, value)

ARGS = {
    'temperature': 0.07,
    'base_temperature': 0.07,
    'layer_penalty': custom_layer_penalty,
    'loss_type': 'hmce'
}
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 HMLC — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a HMLC 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
unique Ran
ran; our contract draft was wrong, not the code
salesforce/hierarchicalcontrastivelearning/losses/losses.py
code served (permissive licence) · get_code("7dfb4b3a59ee93f2")
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. 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

torch.manual_seed(0)

# Create a small 2D tensor with some duplicate rows
x = torch.tensor([
    [1, 2, 3, 4],
    [1, 2, 3, 4],
    [5, 6, 7, 8],
    [1, 2, 3, 4]
], dtype=torch.int64)

ARGS = {
    "x": x,
    "dim": 0
}
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 — 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

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, 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 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.

FunctionAlso present inEarliest-datedOthers named
unique
brick of this paper's assembly: helper
3 other papers
3 later
2023.findings-emnlp.594 (2023 (year only))
Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification
2403.12499 (2024-03)
Listwise Generative Retrieval Models via a Sequential Learning Process
2406.05391 (2024-06)
DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

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

Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks. In this paper, we present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint. The loss function is data driven and automatically adapts to arbitrary multi-label structures. Experiments on several datasets show that our relationship-preserving embedding performs well on a variety of tasks and outperform the baseline supervised and self-supervised approaches. Code is available at https://github.com/salesforce/ hierarchicalContrastiveLearning.

For agents

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

get_harvested_code_for_paper("2204.13207")
get_code_for_paper("2204.13207")
have("2204.13207")

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

curl https://syntology.ai/api/ran/2204.13207.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.13207.svg)](https://syntology.ai/paper/2204.13207)

Connect an agent — have() is free.