SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.01514 · ICML · 2024

Mapping the Multiverse of Latent Representations

Bastian Rieck, Corinna Coupette, Jeremy Wayland

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 2 honoured the contract we drafted, 0 violated it and 0 have 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/2402.01514.json · badge: /api/ran/2402.01514.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
aidos-lab/Presto canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
extract_yaml_id Ran
ran, honoured the contract we drafted
aidos-lab/Presto/lsd/utils.py
code served (permissive licence) · get_code("2e28a7fa1a0118fe")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was 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 re

def extract_yaml_id(file_path):
    """
    Extract the integer identifier from a YAML file path.

    This function uses a regular expression to find and return the integer
    that precedes the ".yml" extension in a file path.

    Parameters
    ----------
    file_path : str
        The path to the YAML file.

    Returns
    -------
    int or None
        The extracted integer identifier, or None if not found.

    Examples
    --------
    >>> extract_yaml_id("universe_42.yml")
    42
    >>> extract_yaml_id("config.yml")
    None
    """
    match = re.search('_(\\d+)\\.yml$', file_path)
    if match:
        return int(match.group(1))
    return None


ARGS = {
    "file_path": "universe_42.yml"
}
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 int, ndim 0, dtype family int, shape () — shape () 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
file_id_sorter Ran
ran, honoured the contract we drafted
aidos-lab/Presto/lsd/utils.py
code served (permissive licence) · get_code("d580b28f76c19db2")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was 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 re

def file_id_sorter(file_name):
    """
    Sort files by their numeric identifiers.

    This function extracts the integer identifier from a filename and
    returns it, allowing for numerical sorting of files with similar names.

    Parameters
    ----------
    file_name : str
        The name of the file.

    Returns
    -------
    int or float
        The extracted integer identifier, or float('inf') if not found.

    Examples
    --------
    >>> file_id_sorter("universe_5.yml")
    5
    >>> file_id_sorter("other_file.txt")
    inf
    """
    match = re.search('universe_(\\d+)\\.yml', file_name)
    return int(match.group(1)) if match else float('inf')


ARGS = {
    "file_name": "universe_42.yml"
}
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 int, ndim 0, dtype family int, shape () — shape () 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
get_parameters Ran
ran; our contract draft was wrong, not the code
aidos-lab/Presto/lsd/utils.py
code served (permissive licence) · get_code("281e62c87492afd4")
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. 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
from inspect import signature

torch.manual_seed(0)

# Create a minimal operator class with some parameters
class SimpleOperator(nn.Module):
    def __init__(self, input_dim=4, output_dim=3, learning_rate=0.001, hidden_size=8):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal config class that supports .get() method
class ProjectorConfig(dict):
    def __init__(self):
        super().__init__()
        self['input_dim'] = 4
        self['output_dim'] = 3
        self['learning_rate'] = 0.001
        self['hidden_size'] = 8
    
    def get(self, key, default=None):
        return super().get(key, default)

# Instantiate the config
config = ProjectorConfig()

ARGS = {
    'Operator': SimpleOperator,
    'config': config
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Echoing recent calls to counter reliability and robustness concerns in machine learning via multiverse analysis, we present PRESTO, a principled framework for mapping the multiverse of machine-learning models that rely on latent representations. Although such models enjoy widespread adoption, the variability in their embeddings remains poorly understood, resulting in unnecessary complexity and untrustworthy representations. Our framework uses persistent homology to characterize the latent spaces arising from different combinations of diverse machinelearning methods, (hyper)parameter configurations, and datasets, allowing us to measure their pairwise (dis)similarity and statistically reason about their distributions. As we demonstrate both theoretically and empirically, our pipeline preserves desirable properties of collections of latent representations, and it can be leveraged to perform sensitivity analysis, detect anomalous embeddings, or efficiently and effectively navigate hyperparameter search spaces.

For agents

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

get_harvested_code_for_paper("2402.01514")
get_code_for_paper("2402.01514")
have("2402.01514")

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

curl https://syntology.ai/api/ran/2402.01514.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.01514.svg)](https://syntology.ai/paper/2402.01514)

Connect an agent — have() is free.