SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.01352 · 2026

Spatiotemporal Proximal Causal Inference under Hidden Confounding and Interference

Jianwu Wang, Omar Faruque, Raj Ravi

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 no recorded run); 2 of them were also run on the host, not in the jail, by the peer-agreement lane that set their level, measured 2026-11-22; 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/2608.01352.json · badge: /api/ran/2608.01352.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
moprescu/Spatial-Deconfounder canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
moprescu/GSTUNet canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
count_parameters Ran
ran, honoured the contract we drafted
moprescu/GSTUNet/train/train_gstunet.py
code served (permissive licence) · get_code("72d1da8e0197ae5f")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:23:38Z). 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Build a small model with trainable parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
pad_func Ran
ran; our contract draft was wrong, not the code
moprescu/GSTUNet/train/wildfire_experiment.py
code served (permissive licence) · get_code("ad1cc25d79162864")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 48, 48) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T01:26:29Z). 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a tensor of shape [B, C, 40, 44]
# B=2 (batch), C=4 (channels), H=40, W=44
x = torch.randn(2, 4, 40, 44)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 48, 48) — shape (2, 4, 48, 48) 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
crop_func Ran
ran, violated the contract we drafted
moprescu/GSTUNet/train/wildfire_experiment.py
code served (permissive licence) · get_code("e506ff823b315c79")
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 Tensor, ndim 4, dtype family float, shape (0, 0, 48, 48) 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 torch

torch.manual_seed(0)

# Create a tensor of shape [B, C, 48, 48]
# B=2 (batch), C=4 (channels), 48x48 spatial dimensions
x = torch.randn(2, 4, 48, 48)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (0, 0, 48, 48) — shape (0, 0, 48, 48) 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
delete_grid Ran
ran; our contract draft was wrong, not the code
moprescu/Spatial-Deconfounder/space-data/utils.py
pointer only (licence: NONE) · get_code("07b0395cdf5b4239")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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.

graph_data_loader Ran
ran; our contract draft was wrong, not the code
moprescu/Spatial-Deconfounder/space-data/train_spaceenv.py
pointer only (licence: NONE) · get_code("52ac8a52c7d09de1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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.

group_by_feat Ran
ran; our contract draft was wrong, not the code
moprescu/Spatial-Deconfounder/space-data/utils.py
pointer only (licence: NONE) · get_code("b3ca07de8312e86d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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.

group_by_feat_graph Ran
ran; our contract draft was wrong, not the code
moprescu/Spatial-Deconfounder/space-data/utils.py
pointer only (licence: NONE) · get_code("3251ed8c3b2488ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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.

make_predict_with_fixed_index Ran
ran; our contract draft was wrong, not the code
moprescu/Spatial-Deconfounder/space-data/train_spaceenv.py
pointer only (licence: NONE) · get_code("32761a6201e6a92c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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.

pad_center Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
moprescu/Spatial-Deconfounder/benchmarks/sci/algorithms/deconfounder.py
pointer only (licence: NONE) · get_code("62098623afc2eb30")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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.

graph_data_loader Not yet run
unverified (harvested, no recorded run)
moprescu/Spatial-Deconfounder/space-data/models/gnn.py
pointer only (licence: NONE) · get_code("d8d285962518f673")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moprescu/Spatial-Deconfounder when it was checked. 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 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
count_parameters 180 other papers
180 dated earlier · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
crop_func 1 other paper
1 dated earlier
2502.05295 (2025-02)
GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
pad_func 1 other paper
1 dated earlier
2502.05295 (2025-02)
GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

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

Estimating causal effects from real-world spatiotemporal data is challenging due to two compounding challenges: hidden confounders that evolve jointly over space and time, and interference, whereby a unit's outcome is caused by its own and its neighbors' treatment. Standard causal identification methods assume conditional exchangeability given observed covariates, which fails whenever unmeasured spatiotemporal confounders affect both treatment assignment and outcomes -a common setting in domains such as climate, environmental policy, epidemiology, and regional economics. In this paper, we propose a novel spatiotemporal proximal causal inference framework that extends proximal identification theory to spatiotemporal settings. The proposed method jointly captures local and neighborhood-level confounding information by introducing treatment-and outcome-inducing proxies, and we derive a spatiotemporal outcome confounding bridge function that identifies the potential outcome without requiring direct recovery of the hidden confounder. We establish the identifiability of this bridge function under a set of proxy exclusion restrictions and a spatiotemporal completeness condition, and show that the resulting estimator recovers the average treatment effect through a proximal generalization of the g-computation formula. To operationalize this identification result, we propose a neural architecture that learns proxies via transformer-based spatiotemporal encoders -coupled with a conditional mutual information critic to enforce exclusion restrictions and a moment-matching network to guarantee that the learned bridge function satisfies the underlying identifying equation rather than reducing to an unconstrained regression. We further introduce a stabilized weighting scheme to address treatment support imbalance under continuous, spatially correlated interventions. Experiments on synthetic datasets demonstrate that our approach achieves comparable performance to state-of-the-art spatiotemporal causal inference methods, while providing, to our knowledge, the first theoretically grounded outcomes for the hidden confounding in the presence of spatiotemporal interference through a proximal causal inference framework.

For agents

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

get_harvested_code_for_paper("2608.01352")
get_code_for_paper("2608.01352")
have("2608.01352")

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

curl https://syntology.ai/api/ran/2608.01352.json

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

[![Syntology run record](https://syntology.ai/api/ran/2608.01352.svg)](https://syntology.ai/paper/2608.01352)

Connect an agent — have() is free.