SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.16109 · NeurIPS · 2020

Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks

Pietro Liò, Emma Rocheteau, Stephanie Hyland

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 2 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/2006.16109.json · badge: /api/ran/2006.16109.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
EmmaRocheteau/TPC-LoS-prediction canonical (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
FunctionStatusWhere it lives
EmptyModule Ran
ran on a synthesized input · constructed an object; no result was computed
EmmaRocheteau/TPC-LoS-prediction/models/tpc_model.py
code served (permissive licence) · get_code("b2d96befce7a24c3")
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 an instance of its own class, EmptyModule: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

class EmptyModule(nn.Module):
    def forward(self, X):
        return X

# Create a small input tensor
X = torch.randn(2, 4)

# EmptyModule only takes self as a parameter (X is passed to forward, not __init__)
# The __init__ method inherits from nn.Module and takes no additional arguments
ARGS = {}
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 EmptyModule — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a EmptyModule 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
MSELoss Ran
ran on a synthesized input
EmmaRocheteau/TPC-LoS-prediction/models/tpc_model.py
code served (permissive licence) · get_code("6d47c3749e547bc2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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 torch
import torch.nn as nn

# INIT_ARGS for MSELoss.__init__()
INIT_ARGS = {}

# ARGS for MSELoss.forward()
batch_size = 2
seq_len = 5
feature_dim = 4

y_hat = torch.randn(batch_size, feature_dim)
y = torch.randn(batch_size, feature_dim)
mask = torch.tensor([[True, True, False, True], [True, False, True, True]])
seq_length = torch.tensor([3, 3], dtype=torch.float32)
sum_losses = False

ARGS = {
    'y_hat': y_hat,
    'y': y,
    'mask': mask,
    'seq_length': seq_length,
    'sum_losses': sum_losses
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
MSLELoss Ran
ran on a synthesized input
EmmaRocheteau/TPC-LoS-prediction/models/tpc_model.py
code served (permissive licence) · get_code("93f875bddc7d0964")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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 torch
import torch.nn as nn

class MSLELoss(nn.Module):

    def __init__(self):
        super(MSLELoss, self).__init__()
        self.squared_error = nn.MSELoss(reduction='none')

    def forward(self, y_hat, y, mask, seq_length, sum_losses=False):
        log_y_hat = y_hat.log().where(mask, torch.zeros_like(y))
        log_y = y.log().where(mask, torch.zeros_like(y))
        loss = self.squared_error(log_y_hat, log_y)
        loss = torch.sum(loss, dim=1)
        if not sum_losses:
            loss = loss / seq_length.clamp(min=1)
        return loss.mean()


INIT_ARGS = {}

ARGS = {
    'y_hat': torch.tensor([[1.5, 2.0, 3.5, 1.2], [2.1, 1.8, 2.5, 3.0]], dtype=torch.float32),
    'y': torch.tensor([[1.2, 2.2, 3.0, 1.5], [2.0, 1.9, 2.8, 2.9]], dtype=torch.float32),
    'mask': torch.tensor([[True, True, True, False], [True, True, False, True]], dtype=torch.bool),
    'seq_length': torch.tensor([3, 3], dtype=torch.long),
    'sum_losses': False
}

if __name__ == '__main__':
    model = MSLELoss(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output: {output}")
    print(f"Output shape: {output.shape}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
MyBatchNorm1d Ran
ran on a synthesized input · constructed an object; no result was computed
EmmaRocheteau/TPC-LoS-prediction/models/tpc_model.py
code served (permissive licence) · get_code("1817e07fcaa33844")
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 an instance of its own class, MyBatchNorm1d: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# MyBatchNorm1d expects 2D or 3D input
# For a 2D input: (batch_size, num_features)
# For a 3D input: (batch_size, num_features, length)

num_features = 4
batch_size = 2

# Create a 2D input tensor (batch_size, num_features)
input_tensor = torch.randn(batch_size, num_features)

# Create an instance of MyBatchNorm1d
bn = nn.BatchNorm1d(num_features, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)

ARGS = {
    "num_features": num_features,
    "eps": 1e-05,
    "momentum": 0.1,
    "affine": True,
    "track_running_stats": True,
}
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 MyBatchNorm1d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MyBatchNorm1d 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
MyBatchNorm Not yet run
unverified (harvested, no recorded run)
EmmaRocheteau/TPC-LoS-prediction/models/tpc_model.py
code served (permissive licence) · get_code("8fa2242b181f9a56")
How it ran

no invocation recorded.

TempPointConv Not yet run
unverified (harvested, no recorded run)
EmmaRocheteau/TPC-LoS-prediction/models/tpc_model.py
code served (permissive licence) · get_code("47bc36c5c6854975")
How it ran

no invocation recorded.

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 present a new deep learning architecture based on the combination of temporal convolution and pointwise (1x1) convolution to predict length of stay on the eICU critical care dataset. The model -which we refer to as Temporal Pointwise Convolution (TPC) -is specifically designed to mitigate for common challenges with Electronic Health Records (EHRs), such as skewness, irregular sampling and missing data. In doing so, we have achieved significant performance benefits of 18-51% (metric dependent) over the commonly used Long-Short Term Memory (LSTM) network, and the Transformer, a multi-head self-attention network.

For agents

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

get_harvested_code_for_paper("2006.16109")
get_code_for_paper("2006.16109")
have("2006.16109")

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

curl https://syntology.ai/api/ran/2006.16109.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.16109.svg)](https://syntology.ai/paper/2006.16109)

Connect an agent — have() is free.