SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.04056 · 2023

Multi-View Causal Representation Learning with Partial Observability

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 5 failures of our instrument; 4 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/2311.04056.json · badge: /api/ran/2311.04056.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
causallearningai/multiview-crl canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_importance_gbt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
causallearningai/multiview-crl/dci.py
code served (permissive licence) · get_code("170d8b2c7bff0cd3")
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 numpy as np

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

# Create small test data
# num_codes = 4 (number of features/codes)
# num_factors = 3 (number of factors)
num_codes = 4
num_factors = 3
num_samples_train = 10
num_samples_test = 5

# x_train: shape [num_codes, num_samples_train] - features for training
x_train = np.random.randn(num_codes, num_samples_train).astype(np.float64)

# y_train: shape [num_factors, num_samples_train] - targets for training
# Mix of discrete and continuous values
y_train = np.random.randn(num_factors, num_samples_train).astype(np.float64)
y_train[0, :] = (y_train[0, :] > 0).astype(np.float64)  # Make first factor discrete (0/1)

# x_test: shape [num_codes, num_samples_test] - features for testing
x_test = np.random.randn(num_codes, num_samples_test).astype(np.float64)

# y_test: shape [num_factors, num_samples_test] - targets for testing
y_test = np.random.randn(num_factors, num_samples_test).astype(np.float64)
y_test[0, :] = (y_test[0, :] > 0).astype(np.float64)  # Make first factor discrete (0/1)

# factor_types: list of strings indicating 'discrete' or 'continuous'
factor_types = ['discrete', 'continuous', 'continuous']

ARGS = {
    'x_train': x_train,
    'y_train': y_train,
    'x_test': x_test,
    'y_test': y_test,
    'factor_types': factor_types,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, six, sklearn — 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
construct_invertible_mlp Ran
ran; our contract draft was wrong, not the code
causallearningai/multiview-crl/invertible_network_utils.py
code served (permissive licence) · get_code("3ccb71a3d6deb62b")
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 Sequential. 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
from scipy.stats import ortho_group
from torch import nn

torch.manual_seed(0)

ARGS = {
    'n': 4,
    'n_layers': 2,
    'n_iter_cond_thresh': 100,
    'cond_thresh_ratio': 0.25,
    'weight_matrix_init': 'pcl',
    'act_fct': 'leaky_relu',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch, typing_extensions — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_mlp Ran
ran; our contract draft was wrong, not the code
causallearningai/multiview-crl/encoders.py
code served (permissive licence) · get_code("f029699ecdd0a5b1")
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 Sequential. 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 typing import List, Union
from typing_extensions import Literal

torch.manual_seed(0)

ARGS = {
    "n_in": 4,
    "n_out": 3,
    "layers": [8, 6],
    "layer_normalization": "bn",
    "output_normalization": None,
    "output_normalization_kwargs": None,
    "act_inf_param": 0.01,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, typing_extensions — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
powerset Ran
ran; our contract draft was wrong, not the code
causallearningai/multiview-crl/utils.py
code served (permissive licence) · get_code("99a88e5f37a92f0d")
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
import numpy as np
from itertools import chain, combinations

# Define a simple iterable with distinct elements
views = ['view_0', 'view_1', 'view_2']

ARGS = {
    'iterable': views,
    'only_consider_whole_set': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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
retrieve_content_style Ran
ran; our contract draft was wrong, not the code
causallearningai/multiview-crl/utils.py
code served (permissive licence) · get_code("d02c1502ca1f036a")
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
import numpy as np

torch.manual_seed(0)

# The function takes a list of zs where each z can be converted to a list
# and treated as a set of elements. We need to create a structure that:
# 1. Can be converted to a list via .tolist()
# 2. Contains multiple views (zs[0], zs[1], etc.)
# 3. Each view should have some common and some unique elements

# Create a tensor-like structure that represents multiple latent vectors
# Each row represents a view, and the values represent latent dimensions/codes
# We'll use a tensor with some overlapping values across views

zs_data = torch.tensor([
    [1, 2, 3, 4],
    [2, 3, 5, 6],
    [1, 2, 7, 8]
], dtype=torch.int64)

ARGS = {
    "zs": zs_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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
compute_gt_idx Not yet run
unverified (harvested, no recorded run)
causallearningai/multiview-crl/main_multimodal.py
code served (permissive licence) · get_code("6ddacf82b281e161")
How it ran

no invocation recorded.

content_style_from_subsets Not yet run
unverified (harvested, no recorded run)
causallearningai/multiview-crl/utils.py
code served (permissive licence) · get_code("fa37808e505554e0")
How it ran

no invocation recorded.

infonce_base_loss Not yet run
unverified (harvested, no recorded run)
causallearningai/multiview-crl/losses.py
code served (permissive licence) · get_code("c777641e597bbeab")
How it ran

no invocation recorded.

infonce_loss Not yet run
unverified (harvested, no recorded run)
causallearningai/multiview-crl/losses.py
code served (permissive licence) · get_code("9d41b2149e408698")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 7 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
infonce_base_loss 1 other paper
1 later
2405.13888 (2024-05)
Marrying Causal Representation Learning with Dynamical Systems for Science
infonce_loss 1 other paper
1 later
2405.13888 (2024-05)
Marrying Causal Representation Learning with Dynamical Systems for Science

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

We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a nonlinear mixture of a subset of underlying latent variables, which can be causally related. We prove that the information shared across all subsets of any number of views can be learned up to a smooth bijection using contrastive learning and a single encoder per view. We also provide graphical criteria indicating which latent variables can be identified through a simple set of rules, which we refer to as identifiability algebra. Our general framework and theoretical results unify and extend several previous works on multi-view nonlinear ICA, disentanglement, and causal representation learning. We experimentally validate our claims on numerical, image, and multi-modal data sets. Further, we demonstrate that the performance of prior methods is recovered in different special cases of our setup. Overall, we find that access to multiple partial views enables us to identify a more fine-grained representation, under the generally milder assumption of partial observability.

For agents

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

get_harvested_code_for_paper("2311.04056")
get_code_for_paper("2311.04056")
have("2311.04056")

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

curl https://syntology.ai/api/ran/2311.04056.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.04056.svg)](https://syntology.ai/paper/2311.04056)

Connect an agent — have() is free.