Pith. sign in

REVIEW 9 cited by

Towards Causal Representation Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.11107 v1 pith:7DFRJAGO submitted 2021-02-22 cs.LG cs.AI

classification cs.LGcs.AI
keywords learningcausalcausalitymachinefieldsrepresentationresearchvariables
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The two fields of machine learning and graphical causality arose and developed separately. However, there is now cross-pollination and increasing interest in both fields to benefit from the advances of the other. In the present paper, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Estimation-Prediction Tradeoff in Causal Probabilistic Temporal Graphs

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Characterizes an estimation-prediction tradeoff in binary logistic models for causal probabilistic temporal graphs and proposes a framework to jointly evaluate temporal link prediction with causal parameter recovery v...

  2. DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.

  3. Creative Robot Tool Use by Counterfactual Reasoning

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    Robots discover causal tool features through VLM suggestions and physics-based counterfactual perturbations in simulation, then transfer manipulation skills via conditioned keypoint matching.

  4. Why Do Large Language Models Generate Harmful Content?

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    Causal mediation analysis shows harmful LLM outputs arise in late layers from MLP failures and gating neurons, with early layers handling harm context detection and signal propagation.

  5. Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure

    cs.AI 2026-02 conditional novelty 6.0 of 10

    Latent CoT steps are causally heterogeneous and non-local: a few steps dominate, influence skips adjacent steps, and output commitment precedes representational commitment.

  6. Causal Discovery from Heteroscedastic Stochastic Dynamical Systems under Imperfect Physical Models

    cs.LG 2026-02 unverdicted novelty 6.0 of 10

    Integrates partial ODE physics into SDE-based causal discovery via drift-diffusion separation, with sparsity-inducing quasi-likelihood estimation, recovery guarantees for stable/unstable systems, and robustness analys...

  7. Modular Foundation Models for Time-Series Perception in Digital Twins

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A gated bank of frozen self-supervised time-series encoders, aligned and aggregated by a Transformer, supports competitive multi-task perception for digital twins and hydro-generator virtual sensing.

  8. Estimation-Prediction Tradeoff in Causal Probabilistic Temporal Graphs

    cs.LG 2026-06 conditional novelty 5.0 of 10

    In binary logistic temporal-graph models, higher Fisher information for parameter recovery coincides with higher irreducible predictive entropy, so the easiest-to-estimate regimes are the hardest to predict.

  9. Platonic Projection Structures: Operator-Induced Observability in Representation Learning

    cs.LG 2026-07 reject novelty 2.0 of 10

    The paper introduces 'Platonic Projection Structures,' a reformulation of standard PSD operator theory applied to representation learning, with experiments that verify definitions rather than test predictions.

Pith tools