SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.09172 · ICML · 2023

Hyperbolic Image-Text Representations

Maximilian Nickel, Ramakrishna Vedantam, Karan Desai, Justin Johnson, Tanmay Rajpurohit

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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; 3 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 6 failures of our instrument; 3 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/2304.09172.json · badge: /api/ran/2304.09172.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
facebookresearch/slip canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
facebookresearch/meru canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
naver-ai/hype community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/slip/main_linear.py
pointer only (licence: MIT) · get_code("131a82fd65128218")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/slip/eval_zeroshot.py
pointer only (licence: MIT); the stored copy get_code serves, from KishoreP1/DetailCLIP, is pointer only (licence: NONE) · get_code("2e59707d16d21473")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cosine_scheduler Ran
ran, honoured the contract we drafted
facebookresearch/slip/beit_finetuning/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from boyazeng/understand_bias, is pointer only (licence: NONE) · get_code("b700fb0a3496b255")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

expm Ran
ran; our contract draft was wrong, not the code
naver-ai/hype/hyperbolic.py
pointer only (licence: NOASSERTION) · get_code("baf67fde22e8bbee")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver-ai/hype (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_downstream_dataset Ran
ran on a synthesized input
facebookresearch/slip/datasets.py
pointer only (licence: MIT) · get_code("f4d9f26124e665f4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_metric_names Ran
ran; our contract draft was wrong, not the code
facebookresearch/slip/models.py
pointer only (licence: MIT); the stored copy get_code serves, from anonymousmlsubmission/datadistributiontransfer, is pointer only (licence: NOASSERTION) · get_code("345ec4da9f331b85")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from anonymousmlsubmission/datadistributiontransfer, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_num_layer_for_vit Ran
ran, honoured the contract we drafted
facebookresearch/slip/beit_finetuning/optim_factory.py
pointer only (licence: MIT) · get_code("a3448702d6025ce6")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_parameter_groups Ran
ran; our contract draft was wrong, not the code
facebookresearch/slip/beit_finetuning/optim_factory.py
pointer only (licence: MIT); the stored copy get_code serves, from boyazeng/understand_bias, is pointer only (licence: NONE) · get_code("0ef0019514eaaa09")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mean_per_class Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/slip/eval_zeroshot.py
pointer only (licence: MIT); the stored copy get_code serves, from KishoreP1/DetailCLIP, is pointer only (licence: NONE) · get_code("f0eb8193f86d363b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pil_loader Ran
ran, honoured the contract we drafted
facebookresearch/slip/datasets.py
pointer only (licence: MIT) · get_code("41dbe0d4c6e1d565")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train Ran
ran on a synthesized input
facebookresearch/slip/main_linear.py
pointer only (licence: MIT) · get_code("9c147228c1764edd")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

validate Ran
ran on a synthesized input
facebookresearch/slip/main_linear.py
pointer only (licence: MIT) · get_code("3e77a098344bd525")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CLIPBaseline Not yet run
unverified (harvested, no recorded run)
facebookresearch/meru/meru/models.py
pointer only (licence: NOASSERTION) · get_code("834ebe823c8808e3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/meru (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MERU Not yet run
unverified (harvested, no recorded run)
facebookresearch/meru/meru/models.py
pointer only (licence: NOASSERTION) · get_code("37a4a089ca65adf3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/meru (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

yfcc_loader Not yet run
unverified (harvested, no recorded run)
facebookresearch/slip/datasets.py
pointer only (licence: MIT) · get_code("3c4992378ca3d4d0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/slip, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 13 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 2 the same month, 9 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.

FunctionAlso present inEarliest-datedOthers named
accuracy 116 other papers
68 dated earlier, 3 the same month, 43 later, 2 same year, order not determinable · 8 only as an assembly brick
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1610.05820 (2016-10)
Membership Inference Attacks Against Machine Learning Models
1905.03696 (2019-05)
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
and 113 more not named here
pil_loader 66 other papers
25 dated earlier, 38 later, 3 same year, order not determinable
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
and 63 more not named here
cosine_scheduler 26 other papers
8 dated earlier, 1 the same month, 15 later, 2 same year, order not determinable
1905.02244 (2019-05)
Searching for MobileNetV3
136810051 (2022 (year only))
AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
and 23 more not named here
get_parameter_groups 18 other papers
7 dated earlier, 10 later, 1 same year, order not determinable
1905.02244 (2019-05)
Searching for MobileNetV3
136810051 (2022 (year only))
AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
and 15 more not named here
accuracy 13 other papers
6 dated earlier, 5 later, 2 same year, order not determinable
1706.02677 (2017-06)
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
1911.00068 (2019-11)
Confident Learning: Estimating Uncertainty in Dataset Labels
2011.09157 (2020-11)
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
and 10 more not named here
get_num_layer_for_vit 8 other papers
4 dated earlier, 4 later
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
2209.03917 (2022-09)
Exploring Target Representations for Masked Autoencoders
2211.09120 (2022-11)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
and 5 more not named here
mean_per_class 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2112.12750 (2021-12)
SLIP: Self-supervision meets Language-Image Pre-training
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
and 2 more not named here
get_metric_names 3 other papers
2 dated earlier, 1 later
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
2302.13602 (2023-02)
The Role of Pre-training Data in Transfer Learning
2512.12997 (2025-12)
Calibrating Uncertainty for Zero-Shot Adversarial CLIP
get_downstream_dataset 2 other papers
1 dated earlier, 1 same year, order not determinable
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
train 2 other papers
1 dated earlier, 1 same year, order not determinable
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
validate 2 other papers
1 dated earlier, 1 same year, order not determinable
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
yfcc_loader 2 other papers
1 dated earlier, 1 same year, order not determinable
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
CLIPBaseline
brick of this paper's assembly: helper
1 other paper
1 later
2410.06912 (2024-10)
Compositional Entailment Learning for Hyperbolic Vision-Language Models

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

Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP (Radford et al., 2021) do not explicitly capture such hierarchy. We propose MERU, a contrastive model that yields hyperbolic representations of images and text. Hyperbolic spaces have suitable geometric properties to embed tree-like data, so MERU can better capture the underlying hierarchy in image-text datasets. Our results show that MERU learns a highly interpretable and structured representation space while being competitive with CLIP's performance on standard multi-modal tasks like image classification and image-text retrieval. Our code and models are available at: https://github. com/facebookresearch/meru

For agents

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

get_harvested_code_for_paper("2304.09172")
get_code_for_paper("2304.09172")
have("2304.09172")

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

curl https://syntology.ai/api/ran/2304.09172.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.09172.svg)](https://syntology.ai/paper/2304.09172)

Connect an agent — have() is free.