SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.14763 · NeurIPS · 2025

Channel Matters: Estimating Channel Influence for Multivariate Time Series

Zeke Xie, James Kwok, Bo Chen, Muyao Wang, Hongwei Liu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure of our instrument; 0 no recorded run), 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/2408.14763.json · badge: /api/ran/2408.14763.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
flare200020/Chinf community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
grad_batch Ran
ran; our contract draft was wrong, not the code
flare200020/Chinf/anomaly_chinf/utils/grad_batch.py
code served (permissive licence) · get_code("55ef4fd652791a88")
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 list, ndim 3, 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
from torch.autograd import grad
import copy

torch.manual_seed(0)

# Build a minimal iTransformer-like model
class MinimalTransformer(nn.Module):
    def __init__(self):
        super().__init__()
        self.projection = nn.Sequential(
            nn.Linear(4, 8),
            nn.ReLU(),
            nn.Linear(8, 4)
        )
    
    def forward(self, x, arg2, arg3, arg4):
        # x shape: (batch, seq_len, features)
        # Output should match input shape for reconstruction loss
        batch_size, seq_len, num_features = x.shape
        x_flat = x.reshape(batch_size * seq_len, num_features)
        output = self.projection(x_flat)
        output = output.reshape(batch_size, seq_len, num_features)
        return output

# Build a minimal loss function
class ReconstructionLoss(nn.Module):
    def forward(self, outputs, targets):
        # Return loss with shape (B, L, N) as expected by grad_batch
        diff = (outputs - targets) ** 2
        return diff

# Create instances
batch_x = torch.randn(2, 3, 4)  # (batch=2, seq_len=3, features=4)
model = MinimalTransformer()
loss_fn = ReconstructionLoss()

ARGS = {
    'batch_x': batch_x,
    'num_layers': 2,
    'model': model,
    'Loss': loss_fn,
    'reconstruct_num': 1,
    'model_name': 'iTransformer',
    'style': 'channel'
}
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 list, ndim 3, dtype family float — a list 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

The influence function serves as an efficient post-hoc interpretability tool that quantifies the impact of training data modifications on model parameters, enabling enhanced model performance, improved generalization, and interpretability insights without the need for expensive retraining processes. Recently, Multivariate Time Series (MTS) analysis has become an important yet challenging task, attracting significant attention. While channel extremely matters to MTS tasks, channel-centric methods are still largely under-explored for MTS. Particularly, no previous work studied the effects of channel information of MTS in order to explore counterfactual effects between these channels and model performance. To fill this gap, we propose a novel Channel-wise Influence (ChInf) method that is the first to estimate the influence of different channels in MTS. Based on ChInf, we naturally derived two channel-wise algorithms by incorporating ChInf into classic MTS tasks. Extensive experiments demonstrate the effectiveness of ChInf and ChInf-based methods in critical MTS analysis tasks, such as MTS anomaly detection and MTS data pruning. Specifically, our ChInf-based methods rank top-1 among all methods for comparison, while previous influence functions do not perform well on MTS anomaly detection tasks and MTS data pruning problem. This fully supports the superiority and necessity of ChInf. Code is available at https://github.com/flare200020/Chinf.

For agents

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

get_harvested_code_for_paper("2408.14763")
get_code_for_paper("2408.14763")
have("2408.14763")

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

curl https://syntology.ai/api/ran/2408.14763.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.14763.svg)](https://syntology.ai/paper/2408.14763)

Connect an agent — have() is free.