SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.12718 · 2023

Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Data

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 failures 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/2302.12718.json · badge: /api/ran/2302.12718.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
vanderschaarlab/compcate canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
counterfactual_survival_prob_from_discrete_hazard_model Ran
ran on a synthesized input
vanderschaarlab/compcate/src/compcate/dgp/data_utils.py
code served (permissive licence) · get_code("b342dc675e1b77e4")
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, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

def constant_event_model(X, t, a, return_p=False, **kwargs):
    """
    A simple constant hazard model that returns predictions.
    Called with X (n_samples, n_features), t (scalar or array), a (n_samples,)
    Should return (predictions, hazards) if return_p=True
    """
    n_samples = X.shape[0]
    predictions = np.random.uniform(0.1, 0.3, n_samples)
    hazards = np.random.uniform(0.05, 0.2, n_samples)
    return (predictions, hazards)

# Create minimal setup
n_samples = 2
n_features = 4
X = np.random.randn(n_samples, n_features).astype(np.float32)
t = 3

ARGS = {
    'X': X,
    't': t,
    'event_model': constant_event_model,
    'comp_model': constant_event_model,
    'event_model_params': {},
    'comp_model_params': {},
    'surv_type': 'cause-specific',
    'haz_only': False,
    'risk': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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_survivors_from_data Ran
ran on a synthesized input
vanderschaarlab/compcate/src/compcate/dgp/data_utils.py
code served (permissive licence) · get_code("41f189a0b3b78309")
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 seed for reproducibility
np.random.seed(0)

# Create small synthetic data
n_samples = 6
n_features = 4

# X: feature matrix (n_samples x n_features)
X = np.random.randn(n_samples, n_features).astype(np.float32)

# t: time to event or censoring (must be integers >= BASE_T=1)
t = np.array([1, 2, 2, 3, 3, 4], dtype=int)

# delta: event indicator (0 = censored, 1 = event)
delta = np.array([0, 1, 0, 1, 0, 1], dtype=int)

# a: treatment assignment (0 or 1)
a = np.array([0, 1, 0, 1, 0, 1], dtype=int)

# t_horizon: time horizon for survival evaluation
t_horizon = 3

ARGS = {
    'X': X,
    't': t,
    'delta': delta,
    'a': a,
    't_horizon': t_horizon,
    'split_by_a': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
propensity_constant Ran
ran on a synthesized input
vanderschaarlab/compcate/src/compcate/dgp/simulation_building_blocks.py
code served (permissive licence) · get_code("9dd0bdbad7e0970e")
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 ndarray, ndim 1, dtype family int, shape (2,) 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 numpy as np

# Construct valid arguments for propensity_constant
X = np.random.randn(2, 4)  # Small batch of 2 samples, 4 features
return_p = False
xi = 0.5
support_covs = None

ARGS = {
    "X": X,
    "return_p": return_p,
    "xi": xi,
    "support_covs": support_covs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (2,) — shape (2,) 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
propensity_linear Ran
ran on a synthesized input
vanderschaarlab/compcate/src/compcate/dgp/simulation_building_blocks.py
code served (permissive licence) · get_code("e87509e1d46ea09c")
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 ndarray, ndim 1, dtype family int, shape (2,) 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 numpy as np

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

# Construct X: a small array with shape (batch_size, n_features)
# The function uses X[:, support_covs] to index columns, so we need at least 2 columns
# Let's use shape (2, 4) - 2 samples, 4 features
X = np.random.randn(2, 4)

# return_p: boolean flag
return_p = False

# xi: float parameter for the expit scaling
xi = 0.5

# center: boolean flag
center = False

# support_covs: list of column indices to use
support_covs = [0, 1]

# exponent: numeric parameter for raising X to a power
exponent = 1

ARGS = {
    "X": X,
    "return_p": return_p,
    "xi": xi,
    "center": center,
    "support_covs": support_covs,
    "exponent": exponent,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (2,) — shape (2,) 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
rmse Ran
ran on a synthesized input
vanderschaarlab/compcate/src/compcate/experiments/experiment_utils.py
code served (permissive licence) · get_code("78f2721cc89ba916")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 seed for reproducibility
np.random.seed(0)

# Create simple numpy arrays for true and predicted values
true = np.array([1.0, 2.0, 3.0, 4.0])
pred = np.array([1.1, 2.1, 2.9, 3.9])

# Define ARGS dict with all parameters
ARGS = {
    "true": true,
    "pred": pred,
    "normalized": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
short_to_long Ran
ran on a synthesized input
vanderschaarlab/compcate/src/compcate/dgp/data_utils.py
code served (permissive licence) · get_code("ea5d51cc7b6402aa")
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 seed for reproducibility
np.random.seed(0)

# Create small synthetic data for survival analysis
n_samples = 5
n_features = 4

# X: feature matrix (n_samples x n_features)
X = np.random.randn(n_samples, n_features)

# t: event times (must be integers, will be used with range)
t = np.array([1, 2, 2, 3, 4], dtype=int)

# delta: event indicator (0 = censored, 1 = event)
delta = np.array([0, 1, 0, 1, 0], dtype=int)

# a: treatment assignment (optional, 1D array)
a = np.array([0, 1, 0, 1, 1], dtype=int)

# t_max: maximum time (optional)
t_max = 3

# weights_by_t_control: weights for control group by time
# Shape: (n_samples, t_max) - weights indexed by (subject, time - BASE_T)
weights_by_t_control = np.random.rand(n_samples, t_max)

# weights_by_t_treated: weights for treated group by time
# Shape: (n_samples, t_max)
weights_by_t_treated = np.random.rand(n_samples, t_max)

ARGS = {
    "X": X,
    "t": t,
    "delta": delta,
    "a": a,
    "t_max": t_max,
    "weights_by_t_control": weights_by_t_control,
    "weights_by_t_treated": weights_by_t_treated,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

We study the problem of inferring heterogeneous treatment effects (HTEs) from time-to-event data in the presence of competing events. Albeit its great practical relevance, this problem has received little attention compared to its counterparts studying HTE estimation without time-to-event data or competing events. We take an outcome modeling approach to estimating HTEs, and consider how and when existing prediction models for time-to-event data can be used as plug-in estimators for potential outcomes. We then investigate whether competing events present new challenges for HTE estimation -- in addition to the standard confounding problem --, and find that, because there are multiple definitions of causal effects in this setting -- namely total, direct and separable effects --, competing events can act as an additional source of covariate shift depending on the desired treatment effect interpretation and associated estimand. We theoretically analyze and empirically illustrate when and how these challenges play a role when using generic machine learning prediction models for the estimation of HTEs.

For agents

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

get_harvested_code_for_paper("2302.12718")
get_code_for_paper("2302.12718")
have("2302.12718")

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

curl https://syntology.ai/api/ran/2302.12718.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.12718.svg)](https://syntology.ai/paper/2302.12718)

Connect an agent — have() is free.