SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.09368 · 2023

Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 1 has no contract verdict; 0 failures of our instrument; 1 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/2306.09368.json · badge: /api/ran/2306.09368.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
imjiawen/warpformer canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
eval_epoch Ran
ran on a synthesized input
imjiawen/warpformer/Main_warp.py
code served (permissive licence) · get_code("479885353ad48e2d")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import numpy as np

torch.manual_seed(0)

# Build a minimal model that satisfies the function's usage
class DummyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def forward(self, observed_tp, observed_data, observed_mask, tau):
        # Returns output that will be passed to classifier
        batch_size = observed_data.shape[0]
        return torch.randn(batch_size, 16)

# Build a minimal classifier
class DummyClassifier(nn.Module):
    def __init__(self, task='mc'):
        super().__init__()
        self.task = task
        if task == 'wbm':
            self.linear = nn.Linear(16, 1)
        else:
            self.linear = nn.Linear(16, 3)  # n_classes=3
    
    def forward(self, x):
        return self.linear(x)

# Build minimal config object
class DummyOpt:
    def __init__(self):
        self.device = 'cpu'
        self.num_types = 4
        self.task = 'mc'  # or 'active' or 'wbm'
        self.n_classes = 3
        self.save_res = '/tmp/test'

# Create validation data as list of batches
# Each batch is (train_batch, labels)
# train_batch shape: (batch_size, seq_len, 3*num_types+1)
# For num_types=4: 3*4+1=13 features
def create_validation_batch(batch_size=2, seq_len=5, num_types=4, task='mc'):
    # train_batch: [batch, seq_len, 3*num_types+1]
    # Columns: [observed_data (num_types), observed_mask (num_types), observed_tp (1), tau (num_types)]
    train_batch = torch.randn(batch_size, seq_len, 3 * num_types + 1)
    
    # Set observed_tp (column 2*num_types) to have a valid argmax
    train_batch[:, :, 2 * num_types] = torch.arange(seq_len).float().unsqueeze(0).expand(batch_size, -1)
    
    if task == 'wbm':
        labels = torch.randint(0, 2, (batch_size,)).float()
    elif task == 'active':
        labels = torch.randint(0, 3, (batch_size * seq_len,))
    else:  # 'mc'
        labels = torch.randint(0, 3, (batch_size,))
    
    return (train_batch, labels)

# Create validation data loader
validation_data = [create_validation_batch(batch_size=2, seq_len=5, num_types=4, task='mc') for _ in range(2)]

# Create loss function
pred_loss_func = nn.CrossEntropyLoss(reduction='none')

# Create model and classifier
model = DummyModel()
classifier = DummyClassifier(task='mc')

# Create options
opt = DummyOpt()

ARGS = {
    'model': model,
    'validation_data': validation_data,
    'pred_loss_func': pred_loss_func,
    'opt': opt,
    'classifier': classifier,
    'save_res': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
train_epoch Not yet run
unverified (harvested, no recorded run)
imjiawen/warpformer/Main_warp.py
code served (permissive licence) · get_code("e76653522ea4067f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Irregularly sampled multivariate time series are ubiquitous in various fields, particularly in healthcare, and exhibit two key characteristics: intra-series irregularity and inter-series discrepancy. Intra-series irregularity refers to the fact that time-series signals are often recorded at irregular intervals, while inter-series discrepancy refers to the significant variability in sampling rates among diverse series. However, recent advances in irregular time series have primarily focused on addressing intra-series irregularity, overlooking the issue of inter-series discrepancy. To bridge this gap, we present Warpformer, a novel approach that fully considers these two characteristics. In a nutshell, Warpformer has several crucial designs, including a specific input representation that explicitly characterizes both intra-series irregularity and inter-series discrepancy, a warping module that adaptively unifies irregular time series in a given scale, and a customized attention module for representation learning. Additionally, we stack multiple warping and attention modules to learn at different scales, producing multi-scale representations that balance coarse-grained and fine-grained signals for downstream tasks. We conduct extensive experiments on widely used datasets and a new large-scale benchmark built from clinical databases. The results demonstrate the superiority of Warpformer over existing state-of-the-art approaches.

For agents

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

get_harvested_code_for_paper("2306.09368")
get_code_for_paper("2306.09368")
have("2306.09368")

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

curl https://syntology.ai/api/ran/2306.09368.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.09368.svg)](https://syntology.ai/paper/2306.09368)

Connect an agent — have() is free.