Pith. sign in

REVIEW 1 cited by

Physics in Next-token Prediction

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 2411.00660 v2 pith:XNTJLU7X submitted 2024-11-01 cs.LG cs.AI

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

We discovered the underlying physics in Next-token Prediction (NTP). We identified the law of information conservation within NTP and proposed the First Law of Information Capacity (IC-1), demonstrating that the essence of intelligence emergence in auto-regressive models is fundamentally a process of information transfer. We also introduced Landauer's Principle into NTP, formulating the Second Law of Information Capacity (IC-2), which establishes the relationship between auto-regressive model training and energy consumption. Additionally, we presented several corollaries, which hold practical significance for production practices. Finally, we demonstrate the consistency between the Law of Information Capacity and the Scaling Law for Neural Language Models, the Knowledge Capacity Scaling Laws, and the Scaling Laws for Precision.

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. Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Finetuning forgetting follows a multiplicative scaling law in model size, finetuning tokens, and injected pretraining fraction, with 1% injection nearly eliminating forgetting.

Pith tools