Attribution-State Conformal Forecasting: Residual-Independent Explanation States for Uncertainty Calibration Under Distribution Shift
- 1Department of Computer Science and Information Technology, NED University of Engineering and Technology, Karachi 75270, Pakistan
- 2Department of Electrical Engineering, NED University of Engineering and Technology, Karachi 75270, Pakistan
Abstract
Conformal prediction provides distribution-free coverage under exchangeability, but global calibration can conceal heterogeneous forecast errors. We introduce attribution-state conformal forecasting (ASCF), which learns calibration strata from residual-independent local explanation geometry. Exact TreeSHAP contributions are normalized, embedded in a square-root/Hellinger space, and clustered before residuals or test outcomes are observed. ASCF was evaluated on 1,381,005 source-level greenhouse-gas observations using separate fitting, state-learning, calibration, and test roles. At 90% nominal coverage, ASCF achieved coverage/interval-score pairs of 0.899/1.693 in the terminal temporal evaluation, 0.927/1.622 for unseen sources, and 0.929/2.294 across five leave-one-country-out folds in which ASCF was instantiable. Relative to global CP, interval-score reductions were 15.9%, 13.9%, and 18.6%. ASCF also produced lower paired interval scores than prediction-conditioned, raw-K matched, and country × gas Mondrian CP in three evaluations, with bootstrap support, reinforcing ASCF’s advantage among the residual-independent conditioning strategies evaluated. Persistence and adapted residual-aware grouping attained lower interval scores. Persistence showed stronger point-forecast accuracy, while an ASCF-plus-global-CP fallback policy extended geographic prediction to all eight countries. In a synthetic proof-of-mechanism, attribution states recovered oracle mechanisms better than matched raw-feature clustering (ARI 0.659 versus 0.040). SHAP-representation sensitivity affected state quality. Under exchangeability, a frozen state map inherits group-conditional split-conformal validity; deliberate shift experiments are interpreted empirically.
Related
- When Language Models Misinterpret Uncertainty in Earth System Mechanism Attribution
- SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models
- Volatility-Corrected Prediction Intervals: Locally Adaptive Uncertainty Quantification for Probabilistic Time-Series Forecasting
- Quantum Bayesian Time Series Forecasting with Uncertainty Quantification
- OmniST: Topology-Invariant Spatiotemporal Forecasting with Guaranteed-Coverage Uncertainty at Unseen Sensor Locations
BibTeX
@article{memon2026attributionstate,
title = {{Attribution-State Conformal Forecasting: Residual-Independent Explanation States for Uncertainty Calibration Under Distribution Shift}},
author = {Shiza Riaz Memon and Saad Ahmed Qazi},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14213990},
url = {https://www.mdpi.com/2227-7390/14/21/3990},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Attribution-State Conformal Forecasting: Residual-Independent Explanation States for Uncertainty Calibration Under Distribution Shift
AU - Shiza Riaz Memon
AU - Saad Ahmed Qazi
PY - 2026
DA - 2026/11/02
JO - Mathematics
DO - 10.3390/math14213990
UR - https://www.mdpi.com/2227-7390/14/21/3990
AB - Conformal prediction provides distribution-free coverage under exchangeability, but global calibration can conceal heterogeneous forecast errors. We introduce attribution-state conformal forecasting (ASCF), which learns calibration strata from residual-independent local explanation geometry. Exact TreeSHAP contributions are normalized, embedded in a square-root/Hellinger space, and clustered before residuals or test outcomes are observed. ASCF was evaluated on 1,381,005 source-level greenhouse-gas observations using separate fitting, state-learning, calibration, and test roles. At 90% nominal coverage, ASCF achieved coverage/interval-score pairs of 0.899/1.693 in the terminal temporal evaluation, 0.927/1.622 for unseen sources, and 0.929/2.294 across five leave-one-country-out folds in which ASCF was instantiable. Relative to global CP, interval-score reductions were 15.9%, 13.9%, and 18.6%. ASCF also produced lower paired interval scores than prediction-conditioned, raw-K matched, and country × gas Mondrian CP in three evaluations, with bootstrap support, reinforcing ASCF’s advantage among the residual-independent conditioning strategies evaluated. Persistence and adapted residual-aware grouping attained lower interval scores. Persistence showed stronger point-forecast accuracy, while an ASCF-plus-global-CP fallback policy extended geographic prediction to all eight countries. In a synthetic proof-of-mechanism, attribution states recovered oracle mechanisms better than matched raw-feature clustering (ARI 0.659 versus 0.040). SHAP-representation sensitivity affected state quality. Under exchangeability, a frozen state map inherits group-conditional split-conformal validity; deliberate shift experiments are interpreted empirically.
SN - 2227-7390
ER -