SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.21828 · 2026

CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter

Bin Yang, Yang Shu, Chenjuan Guo, Zhongwen Rao, Lujia Pan, Xingjian Wu, Hanyin Cheng

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 0 violated it and 0 have no contract verdict; 4 failures 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/2603.21828.json · badge: /api/ran/2603.21828.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
decisionintelligence/CoRA canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
decompose_time Ran
ran, honoured the contract we drafted
decisionintelligence/CoRA/ts_benchmark/baselines/utils.py
pointer only (licence: NONE) · get_code("b19d5a8d2ddd9af5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, decisionintelligence/CoRA 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.

encode_params Ran
ran; our contract draft was wrong, not the code
decisionintelligence/CoRA/ts_benchmark/evaluation/evaluator.py
pointer only (licence: NONE); the stored copy get_code serves, from decisionintelligence/TAB, is pointer only (licence: NONE) · get_code("04644b19aad54d7e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, decisionintelligence/CoRA 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.

filter_data Ran
ran; our contract draft was wrong, not the code
decisionintelligence/CoRA/ts_benchmark/pipeline.py
pointer only (licence: NONE) · get_code("005a7fb4e6c758a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, decisionintelligence/CoRA 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.

get_model_hyper_params Ran
ran; our contract draft was wrong, not the code
decisionintelligence/CoRA/ts_benchmark/models/model_loader.py
pointer only (licence: NONE) · get_code("440b2e1ab3bfb5d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, decisionintelligence/CoRA 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.

import_model_info Ran
ran; our contract draft was wrong, not the code
decisionintelligence/CoRA/ts_benchmark/models/model_loader.py
pointer only (licence: NONE) · get_code("85b193fe718a6b6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, decisionintelligence/CoRA 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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
filter_data 6 other papers
3 dated earlier, 2 later, 1 undated
2506.18046 (2025-06)
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
2510.16511 (2025-10)
Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
2510.23672 (2025-10)
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
and 3 more not named here
get_model_hyper_params 6 other papers
3 dated earlier, 2 later, 1 undated
2506.18046 (2025-06)
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
2510.16511 (2025-10)
Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
2510.23672 (2025-10)
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
and 3 more not named here
import_model_info 6 other papers
3 dated earlier, 2 later, 1 undated
2506.18046 (2025-06)
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
2510.16511 (2025-10)
Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
2510.23672 (2025-10)
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
and 3 more not named here
decompose_time 4 other papers
2 dated earlier, 2 later
2506.18046 (2025-06)
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
2510.23672 (2025-10)
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
2604.13924 (2026-04)
ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection
and 1 more not named here
encode_params 3 other papers
2 dated earlier, 1 later
2506.18046 (2025-06)
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
2510.23672 (2025-10)
DBLoss: Decomposition-based Loss Function for Time Series Forecasting
2604.13924 (2026-04)
ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection

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

Most existing Time Series Foundation Models (TSFMs) use channel independent modeling and focus on capturing and generalizing temporal dependencies, while neglecting the correlations among channels or overlooking the different aspects of correlations. However, these correlations play a vital role in Multivariate time series forecasting. To address this, we propose a CoRrelation-aware Adapter (CoRA), a lightweight plug-and-play method that requires only fine-tuning with TSFMs and is able to capture different types of correlations, so as to improve forecast performance. Specifically, to reduce complexity, we innovatively decompose the correlation matrix into low-rank Time-Varying and Time-Invariant components. For the Time-Varying component, we further design learnable polynomials to learn dynamic correlations by capturing trends or periodic patterns. To learn positive and negative correlations that appear only among some channels, we introduce a novel dual contrastive learning method that identifies correlations through projection layers, regulated by a Heterogeneous-Partial contrastive loss during training, without introducing additional complexity in the inference stage. Extensive experiments on 10 real-world datasets demonstrate that CoRA can improve TSFMs in multivariate forecasting performance.

For agents

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

get_harvested_code_for_paper("2603.21828")
get_code_for_paper("2603.21828")
have("2603.21828")

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

curl https://syntology.ai/api/ran/2603.21828.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.21828.svg)](https://syntology.ai/paper/2603.21828)

Connect an agent — have() is free.