4arXiv cs.LG (Machine Learning)·
TimePNS: Counterfactual necessity framework for time-series classifier explanation
A new arXiv preprint introduces TimePNS, a two-stage framework for explaining time-series classifiers using Pearl's counterfactual notion of necessity. The method addresses a gap in existing sufficiency-oriented explanation methods, which can assign high importance to spurious subsequences that support but are not essential to a model's prediction. TimePNS learns a causal generative process and uses counterfactual interventions to identify decision-critical temporal subsequences, reporting improved sufficiency-necessity trade-offs over baselines on synthetic and real-world benchmarks.
Related guides (1)
Related events (8)
Impossibility result: spectral predictability indices cannot predict when context, retrieval, or foundation models help in time-series forecasting
A new arXiv preprint proves an impossibility result showing that power-spectrum-based predictability indices cannot determine whether adding context (longer lookback, retrieval, or pretrained models) will improve time-series forecasting, because such indices are invariant under phase randomization while the value of retrieval and foundation models is not. The authors introduce a label-free diagnostic called the 'coverage deficit' that measures beyond-spectrum structure as the gain of analog over linear prediction. Experiments across seven benchmarks validate the distinction: retrieval value collapses under spectrum-preserving surrogates while spectral indices remain frozen, and the new diagnostic predicts the sign of beyond-spectrum value where spectral indices fail. No new forecaster is introduced; the contribution is the theoretical distinction, controlled comparisons, and a deployment diagnostic.
PCMCI+ extended for causal discovery on irregular time series
A new arXiv preprint proposes an extension of PCMCI+, a leading causal discovery method for multivariate time series, to handle irregularly sampled data by aggregating causal influence over temporal windows rather than fixed lags. The method is evaluated on synthetic irregular event streams with known causal structures across varying signal-to-noise ratios, consistently recovering the underlying causal graph and outperforming standard PCMCI+. This addresses a practical gap for domains like healthcare, sensor networks, and financial transactions where regular sampling is not guaranteed.
Introspective Coupling: LMs trained on fixed counterfactual explanations develop self-faithful introspection
A new arXiv paper studies language models trained to explain their own predictions using counterfactual supervision derived from earlier checkpoints or behaviorally similar models. Surprisingly, models frequently produce explanations more faithful to their current behavior than to the training targets — a phenomenon the authors call 'introspective coupling.' The effect persists across tasks including sycophancy and refusal, tracks concurrent behavioral shifts from other post-training objectives, and is robust to label noise, suggesting fixed counterfactual explanation datasets can serve as scalable post-training signal for introspection.
Prefix Utility Model (PUM) trains process reward models on outcome-grounded prefix gain rather than step correctness
A new arXiv preprint proposes replacing local step-correctness signals in process reward models with 'prefix gain' — the improvement in solve-rate induced by conditioning a student model on a given reasoning prefix. The authors train a Prefix Utility Model (PUM) using a pairwise ranking objective and evaluate it across Best-of-N selection, beam search, and RL on mathematical reasoning tasks. PUM shows particular strength when candidate pools are large, search budgets are high, or rule-based rewards are sparse. Code, data, and models are released publicly.
WorldKernel: Formalizing world models as coupling kernels over counterfactual worlds
A new arXiv preprint identifies a structural failure mode in prediction-based world models: strong predictors can recover the diagonal of a counterfactual coupling kernel (ordinary posteriors) but systematically fail on off-diagonal cross-world couplings, collapsing to point estimates that are sometimes provably inadmissible. The authors formalize a world model as a positive semidefinite kernel K(T,T') over admissible possible worlds, showing the off-diagonal encodes counterfactual structure that more data cannot resolve. They demonstrate that PSD constraints provide partial identification bounds computable in polynomial time, that ontological axioms tighten these bounds, and that targeted constraint learning ('scars') closes the gap faster than untargeted approaches. The work has implications for causal reasoning in AI systems and the theoretical limits of learned world models.
NF-CoT: Latent reasoning with normalizing flows preserves autoregressive LLM advantages
Researchers propose NF-CoT, a latent reasoning framework that replaces discrete chain-of-thought token streams with continuous intermediate states modeled by normalizing flows embedded inside an LLM backbone. The approach uses a TARFlow-style normalizing flow head alongside the standard language model head, enabling exact likelihoods, KV-cache-compatible left-to-right decoding, and policy-gradient optimization in latent space. On code-generation benchmarks, NF-CoT improves pass rates over both explicit CoT and prior latent-reasoning baselines while reducing intermediate reasoning cost. The work addresses a key limitation of existing latent reasoning methods, which typically sacrifice probabilistic tractability or autoregressive compatibility.
Neural Classification Trees (NCT) discover latent subgroups for robust classification without group supervision
A new arXiv preprint introduces Neural Classification Trees (NCT), a framework that encodes subgroup structure in a tree-shaped architecture to address spurious correlations in ML classifiers. By routing samples to 'easy' or 'hard' nodes based on prediction correctness and reusing routes as pseudo-labels iteratively, NCT disentangles conflicting subgroups without requiring subgroup annotations. The method is evaluated on five benchmarks covering binary and multi-class spurious correlations, achieving competitive robustness while providing interpretable mappings between model architecture and latent data structure.
DeepSWIP: Counterfactual reasoning for neural probabilistic logic programs via quotient-WMC
DeepSWIP introduces a single-world counterfactual semantics for DeepProbLog, enabling causal inference over neurosymbolic programs that combine neural perception with probabilistic logic. The approach uses neural materialization to reduce neural predicates to standard ProbLog choices, then applies Single World Intervention Programs (SWIPs) and weighted model counting to compute exact counterfactuals from a single transformed program. Experiments on MPI3D validate the method against a DeepTwin construction across 12,000 queries and show a 2.14× inference speedup, while a SUMO HOV experiment demonstrates that neural calibration degradation biases plug-in causal estimates and that a correctly scoped AIPW estimator removes most first-order bias.