mlsanityData to 14 Oct 2026

Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals

arXiv 2606.20889 ↗First posted 18 Jun 2026cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Estimating causal effects in industrial time series requires handling temporal dynamics, time-varying treatments, and unobserved confounders. Existing causal foundation models (CausalPFN, CausalFM) operate only on static cross-sectional data; neural temporal methods (CRN, G-Net) require per-dataset training; and concurrent temporal-PFN proposals have not been demonstrated at industrial scale. None output explicit per-pair reliability signals alongside their CATE estimates. We introduce Temporal Causal Prior-Data Fitted Networks (TCPFN), a foundation model for zero-shot temporal causal discovery with learned reliability signals. TCPFN makes four contributions: (1) a Causal Judgment Head that jointly predicts null-effect probability, confounding strength, identifiability, mediation fraction, and causal regime; (2) a mixed training prior covering six causal regimes (independent, direct, confounded, mediated, time-varying confounded, feedback) plus CausalFM-style front-door and instrumental-variable priors; (3) a discrete-token panel-data architecture with cross-attention masking that prevents inter-horizon leakage; (4) zero-shot inference at industrial scale via FAISS-based context selection and one-step posterior correction. On 19 benchmark datasets across five domains, TCPFN achieves competitive zero-shot causal discovery: AUROC 0.96 on Tennessee Eastman, 0.93 on SWaT, 0.98 on Causal Rivers, 0.97 on CAUSRCA. The null detector reaches NullF1 0.94, AUROC 0.99. TCPFN scales to V=1,275 on a proprietary Kraft pulp-and-paper dataset in 6 hours on a single GPU; PCMCI, a CPU-only library, on a V=666 sub-panel of the same data took 81.5 hours, extrapolating by O(V^2) to ~12.5 days at V=1,275. TCPFN's top edges identify cross-subsystem causal relationships while PCMCI's surface within-instrument controller-measurement coupling -- a scalability case study.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

17 of 36 references.

References · 17

  1. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  2. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  3. 2021Transformers Can Do Bayesian Inferencecited by 360
  4. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  5. 2017Detecting causal associations in large nonlinear time series datasetscited by 244
  6. 2020Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representationscited by 155
  7. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 123
  8. 2022Deep End-to-end Causal Inferencecited by 95
  9. 2022Amortized Inference for Causal Structure Learningcited by 90
  10. 2022Learning to Induce Causal Structurecited by 68
  11. 2018Improving Regression Performance with Distributional Lossescited by 67
  12. 2025Do-PFN: In-Context Learning for Causal Effect Estimationcited by 51
5 more
  1. 2025Foundation Models for Causal Inference via Prior-Data Fitted Networkscited by 32
  2. 2024Dynamic Structural Causal Modelscited by 14
  3. 2026Interventional Time Series Priors for Causal Foundation Modelscited by 7
  4. 2026Frequentist Consistency of Prior-Data Fitted Networks for Causal Inferencecited by 4
  5. 2026Towards Continuous-time Causal Foundation Modelscited by 4

Built on by

Not cited yet.