Pith. sign in

REVIEW 1 cited by

Predictive Information

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 cond-mat/9902341 v1 pith:EBFF37NQ submitted 1999-02-25 cond-mat.stat-mech cond-mat.dis-nnq-bio.NC

classification cond-mat.stat-mechcond-mat.dis-nnq-bio.NC
keywords informationpredictivecomplexitydatameasuresmodelallowsargue
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Observations on the past provide some hints about what will happen in the future, and this can be quantified using information theory. The ``predictive information'' defined in this way has connections to measures of complexity that have been proposed both in the study of dynamical systems and in mathematical statistics. In particular, the predictive information diverges when the observed data stream allows us to learn an increasingly precise model for the dynamics that generate the data, and the structure of this divergence measures the complexity of the model. We argue that divergent contributions to the predictive information provide the only measure of complexity or richness that is consistent with certain plausible requirements.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Next-token pretraining implies in-context learning

    cs.LG 2025-05 conditional novelty 7.0 of 10

    A well-trained next-token predictor's in-context loss equals the conditional entropy of the data process, which must decrease with context for stationary data.

Pith tools