Paper Citation Record · LEDGER

Compute-Optimal LLMs Provably Generalize Better With Scale

As of 19 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 1 inbound Pith citation observation for arXiv:2504.15208.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.15208 v1

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:38:22.316432Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:07:39.503440Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

65 of 65 outbound references displayed

verified exact1
verified fuzzy28
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7b3cf814-384d-4a92-814d-15bb958031fd · outbound

This paper cites write newline.

Compute-Optimal LLMs Provably Generalize Better With Scale write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.075061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96795756-2584-4300-b416-79dfe1933a1a · outbound

This paper cites Understanding prompt engineering may not require rethinking generalization.

Compute-Optimal LLMs Provably Generalize Better With Scale Understanding prompt engineering may not require rethinking generalization

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.079896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ab4c9f-cb2b-47f6-a73a-75b6da82d5ab · outbound

This paper cites Stronger generalization bounds for deep nets via a compression approach.

Compute-Optimal LLMs Provably Generalize Better With Scale Stronger generalization bounds for deep nets via a compression approach

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.977158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d84c9bb0-e85f-43ad-9058-0150d8bb08f8 · outbound

This paper cites Explaining neural scaling laws.

Compute-Optimal LLMs Provably Generalize Better With Scale Explaining neural scaling laws

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.965870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 44c11671-9354-4433-919c-7ef63e26aaf6 · outbound

This paper cites Chinchilla Scaling: A replication attempt.

Compute-Optimal LLMs Provably Generalize Better With Scale Chinchilla Scaling: A replication attempt

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.092818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a2d3eb-d209-47d2-86d5-37416d71743a · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

Compute-Optimal LLMs Provably Generalize Better With Scale Pythia: A suite for analyzing large language models across training and scaling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.096779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0db98836-ce42-4401-b627-50ca42b6e204 · outbound

This paper cites The description length of deep learning models.

Compute-Optimal LLMs Provably Generalize Better With Scale The description length of deep learning models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.100555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc3d543-7ad7-4e03-b448-69a26a1e5dda · outbound

This paper cites The tradeoffs of large scale learning.

Compute-Optimal LLMs Provably Generalize Better With Scale The tradeoffs of large scale learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.104403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f885886-6807-417f-8db1-acfa8a94417e · outbound

This paper cites Bias/variance is not the same as approximation/estimation.

Compute-Optimal LLMs Provably Generalize Better With Scale Bias/variance is not the same as approximation/estimation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.933298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 363fe238-5f9d-4b71-bbdb-85232bf6262d · outbound

This paper cites Language Models are Few-Shot Learners.

Compute-Optimal LLMs Provably Generalize Better With Scale Language Models are Few-Shot Learners

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.111193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb5bf52f-1a7e-4347-9924-b4fc0865e578 · outbound

This paper cites Cleaning large correlation matrices: tools from random matrix theory.

Compute-Optimal LLMs Provably Generalize Better With Scale Cleaning large correlation matrices: tools from random matrix theory

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.922711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e75924da-6c54-4e14-a1a7-e5a97464db7e · outbound

This paper cites Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning.

Compute-Optimal LLMs Provably Generalize Better With Scale Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.118996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b5f6c3b-3702-4176-a2a1-fd0871ab1ea8 · outbound

This paper cites Quip: 2-bit quantization of large language models with guarantees.

Compute-Optimal LLMs Provably Generalize Better With Scale Quip: 2-bit quantization of large language models with guarantees

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.122850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67746957-f5e9-49d7-aa8f-18f31f8fdedb · outbound

This paper cites A unified recipe for deriving (time-uniform) pac-bayes bounds.

Compute-Optimal LLMs Provably Generalize Better With Scale A unified recipe for deriving (time-uniform) pac-bayes bounds

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.905886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d2643b37-8139-4f60-a096-c99a2ce3f8c8 · outbound

This paper cites an unresolved cited work.

Compute-Optimal LLMs Provably Generalize Better With Scale Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.129893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd27181-e3d3-4054-89ad-c06ff780b013 · outbound

This paper cites Present position and potential developments: Some personal views statistical theory the prequential approach.

Compute-Optimal LLMs Provably Generalize Better With Scale Present position and potential developments: Some personal views statistical theory the prequential approach

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.895212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2df1ef4e-afb7-485e-adcc-315b62827b67 · outbound

This paper cites LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale.

Compute-Optimal LLMs Provably Generalize Better With Scale LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.137161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4744cd00-f691-4daa-8229-1e453028253d · outbound

This paper cites Scalable log determinants for gaussian process kernel learning.

Compute-Optimal LLMs Provably Generalize Better With Scale Scalable log determinants for gaussian process kernel learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.883274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f3bcf3f8-314a-49d7-a0c8-52de742ad0f5 · outbound

This paper cites The Llama 3 Herd of Models.

Compute-Optimal LLMs Provably Generalize Better With Scale The Llama 3 Herd of Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.144884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aceb9ed-75e5-4346-9c47-4b8479e12402 · outbound

This paper cites Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data.

Compute-Optimal LLMs Provably Generalize Better With Scale Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.148737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b464350-61d8-4ed9-81a7-9de9a51e670f · outbound

This paper cites Entropic trace estimates for log determinants.

Compute-Optimal LLMs Provably Generalize Better With Scale Entropic trace estimates for log determinants

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.870952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3cf335c6-2e66-42d3-af3a-29241c302919 · outbound

This paper cites Gptq: Accurate post-training quantization for generative pre-trained transformers, 2023.

Compute-Optimal LLMs Provably Generalize Better With Scale Gptq: Accurate post-training quantization for generative pre-trained transformers, 2023

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.156151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c03c8329-df62-436e-bfa9-4c27f9f7def1 · outbound

This paper cites Freedman.

Compute-Optimal LLMs Provably Generalize Better With Scale Freedman

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.852798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83ef1ba5-b86f-45d7-ab06-dbba6a2fd77f · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Compute-Optimal LLMs Provably Generalize Better With Scale The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.163291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 415087f9-5cab-4215-b5e3-f4f8967eaaab · outbound

This paper cites An investigation into neural net optimization via hessian eigenvalue density.

Compute-Optimal LLMs Provably Generalize Better With Scale An investigation into neural net optimization via hessian eigenvalue density

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.167147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 849ec5a8-8b01-49fa-b315-017752f2caae · outbound

This paper cites Mlrg deep curvature: An open-source package to analyse and visualise neural network curvature and loss surface.

Compute-Optimal LLMs Provably Generalize Better With Scale Mlrg deep curvature: An open-source package to analyse and visualise neural network curvature and loss surface

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.835426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fa6e4084-21b5-4636-9fad-777f63fce707 · outbound

This paper cites The deep learning limit: are negative neural network eigenvalues just noise? In ICML 2019 workshop on theoretical physics for deep learning, 2019.

Compute-Optimal LLMs Provably Generalize Better With Scale The deep learning limit: are negative neural network eigenvalues just noise? In ICML 2019 workshop on theoretical physics for deep learning, 2019

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.824592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f520a299-d2ca-42ef-8d59-032607d860fc · outbound

This paper cites Learning rates as a function of batch size: A random matrix theory approach to neural network training.

Compute-Optimal LLMs Provably Generalize Better With Scale Learning rates as a function of batch size: A random matrix theory approach to neural network training

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.814018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 39d7c201-f8e2-4c71-ad76-0e34123ee9fb · outbound

This paper cites Large language models are zero-shot time series forecasters.

Compute-Optimal LLMs Provably Generalize Better With Scale Large language models are zero-shot time series forecasters

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.803294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b61e3b02-788b-44d7-a5e3-f0f1afe91f81 · outbound

This paper cites Stork, and Gregory J.

Compute-Optimal LLMs Provably Generalize Better With Scale Stork, and Gregory J

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.793136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b86b374e-5705-4024-88c0-4fe718beb772 · outbound

This paper cites Scaling Laws for Autoregressive Generative Modeling.

Compute-Optimal LLMs Provably Generalize Better With Scale Scaling Laws for Autoregressive Generative Modeling

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.188868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2072898-fc0c-4244-8adb-8c9d99a1cc5b · outbound

This paper cites Training Compute-Optimal Large Language Models.

Compute-Optimal LLMs Provably Generalize Better With Scale Training Compute-Optimal Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.192753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a493637-6881-4bd5-9fd9-d11bc7b95fff · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Compute-Optimal LLMs Provably Generalize Better With Scale LoRA: Low-Rank Adaptation of Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.196353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1211ec-96f3-4eca-9d80-0f72d1221657 · outbound

This paper cites Accurate post training quantization with small calibration sets.

Compute-Optimal LLMs Provably Generalize Better With Scale Accurate post training quantization with small calibration sets

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.782355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bb16290f-2d34-40c6-9a84-88fcc7cf36f8 · outbound

This paper cites Scaling Laws for Neural Language Models.

Compute-Optimal LLMs Provably Generalize Better With Scale Scaling Laws for Neural Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.203753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21e07eec-742c-4668-95ab-aacd7d5c7248 · outbound

This paper cites A device for quantizing, grouping, and coding amplitude-modulated pulses.

Compute-Optimal LLMs Provably Generalize Better With Scale A device for quantizing, grouping, and coding amplitude-modulated pulses

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.770579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 354aaba0-32d5-431d-82ff-90a55961e9b4 · outbound

This paper cites Transformers as algorithms: Generalization and stability in in-context learning.

Compute-Optimal LLMs Provably Generalize Better With Scale Transformers as algorithms: Generalization and stability in in-context learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.759739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1ea776a1-dd85-46c6-adef-1c2e2b61731d · outbound

This paper cites Lee, Song Han, Tri Dao, and Tianle Cai.

Compute-Optimal LLMs Provably Generalize Better With Scale Lee, Song Han, Tri Dao, and Tianle Cai

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.748533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f484ace4-4f99-470e-a4a4-5e549bebc658 · outbound

This paper cites Pac-bayes compression bounds so tight that they can explain generalization.

Compute-Optimal LLMs Provably Generalize Better With Scale Pac-bayes compression bounds so tight that they can explain generalization

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.738268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a50627d6-909e-4696-9d89-7346b2e06f0a · outbound

This paper cites an unresolved cited work.

Compute-Optimal LLMs Provably Generalize Better With Scale Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:38:22.727805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c01941a-7b69-47d8-96ff-13dc202e805d · outbound

This paper cites Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models.

Compute-Optimal LLMs Provably Generalize Better With Scale Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.229148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6934890-b0ec-4c67-b391-fd75ad7e994a · outbound

This paper cites The era of 1-bit llms: All large language models are in 1.58 bits, 2024.

Compute-Optimal LLMs Provably Generalize Better With Scale The era of 1-bit llms: All large language models are in 1.58 bits, 2024

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.232959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36286e9a-b7c7-4cf1-88dc-0de0eb1cec8e · outbound

This paper cites Empirical Bernstein Bounds and Sample Variance Penalization.

Compute-Optimal LLMs Provably Generalize Better With Scale Empirical Bernstein Bounds and Sample Variance Penalization

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.236301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c1eeec9-0a2e-4057-aa1c-8fd4d1e1bb56 · outbound

This paper cites Two inequalities implied by unique decipherability.

Compute-Optimal LLMs Provably Generalize Better With Scale Two inequalities implied by unique decipherability

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.709518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1b2f8dfc-9c07-44a1-b66e-f7a6ac24da85 · outbound

This paper cites The lanczos and conjugate gradient algorithms in finite precision arithmetic.

Compute-Optimal LLMs Provably Generalize Better With Scale The lanczos and conjugate gradient algorithms in finite precision arithmetic

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.698534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c020fb14-7aec-4912-86c2-f73e00e9fea3 · outbound

This paper cites Scaling data-constrained language models.

Compute-Optimal LLMs Provably Generalize Better With Scale Scaling data-constrained language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.247008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d810169b-38a5-4842-bb70-6a597dca3954 · outbound

This paper cites Up or down? adaptive rounding for post-training quantization.

Compute-Optimal LLMs Provably Generalize Better With Scale Up or down? adaptive rounding for post-training quantization

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.680484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e00a7dd6-0e83-4b18-9781-a981cefa2c4a · outbound

This paper cites Gpt-4 technical report.

Compute-Optimal LLMs Provably Generalize Better With Scale Gpt-4 technical report

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.254259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf771928-32e8-4534-8178-3f79fa0ff8aa · outbound

This paper cites Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians.

Compute-Optimal LLMs Provably Generalize Better With Scale Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.257738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a77ed7-a18e-4dbc-af46-f3d4fb3a4dbc · outbound

This paper cites Mapping language models to grounded conceptual spaces.

Compute-Optimal LLMs Provably Generalize Better With Scale Mapping language models to grounded conceptual spaces

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.661537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e7743e77-bd73-464e-99cf-a243f138b066 · outbound

This paper cites Fast exact multiplication by the hessian.

Compute-Optimal LLMs Provably Generalize Better With Scale Fast exact multiplication by the hessian

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.265462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7945c6-c682-4553-baa5-aaf78f95b3eb · outbound

This paper cites CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra.

Compute-Optimal LLMs Provably Generalize Better With Scale CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:38:22.410813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e7de62fb-6cc7-4a7e-a39f-d1ef9c980ce5 · outbound

This paper cites Universal coding, information, prediction, and estimation.

Compute-Optimal LLMs Provably Generalize Better With Scale Universal coding, information, prediction, and estimation

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.644397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 53d00811-e41c-48e7-8d16-227f9b68dfbd · outbound

This paper cites Improved bounds on sample size for implicit matrix trace estimators.

Compute-Optimal LLMs Provably Generalize Better With Scale Improved bounds on sample size for implicit matrix trace estimators

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.633627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 46d5a63c-6a49-4806-b51d-e08858ea860b · outbound

This paper cites Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws.

Compute-Optimal LLMs Provably Generalize Better With Scale Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.279976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59b090e3-87f3-4ffb-aaf3-3f6b63d8aec0 · outbound

This paper cites Understanding machine learning: From theory to algorithms.

Compute-Optimal LLMs Provably Generalize Better With Scale Understanding machine learning: From theory to algorithms

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.283762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ea09fc-0164-4d79-a124-ca12a33bf2fd · outbound

This paper cites A formal theory of inductive inference.

Compute-Optimal LLMs Provably Generalize Better With Scale A formal theory of inductive inference

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.615408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 855d97b9-8de3-40e6-a490-826520283181 · outbound

This paper cites Trinh, Yuhuai Wu, Quoc V.

Compute-Optimal LLMs Provably Generalize Better With Scale Trinh, Yuhuai Wu, Quoc V

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.604624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 12c15269-5b54-4fdb-9dbd-0cbb7e78a484 · outbound

This paper cites Quip: Even better llm quantization with hadamard incoherence and lattice codebooks, 2024.

Compute-Optimal LLMs Provably Generalize Better With Scale Quip: Even better llm quantization with hadamard incoherence and lattice codebooks, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:38:22.593492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4385a41d-0cc7-471a-94b5-f01162beb711 · outbound

This paper cites Fast estimation of tr(f(a)) via stochastic lanczos quadrature.

Compute-Optimal LLMs Provably Generalize Better With Scale Fast estimation of tr(f(a)) via stochastic lanczos quadrature

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.298302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12bc52a9-b5c5-4103-a42c-762db9e76861 · outbound

This paper cites Étude critique de la notion de collectif.

Compute-Optimal LLMs Provably Generalize Better With Scale Étude critique de la notion de collectif

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.301721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b4d2b1-a120-4fca-a0f1-c81580b8f8cc · outbound

This paper cites Information-Theoretic Probing with Minimum Description Length.

Compute-Optimal LLMs Provably Generalize Better With Scale Information-Theoretic Probing with Minimum Description Length

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.305478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a49b61a-c3c2-46dd-a9a7-c8c2c44b479b · outbound

This paper cites ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers.

Compute-Optimal LLMs Provably Generalize Better With Scale ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.309181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa136ff-7aef-4a09-a51d-bd80912c5e2e · outbound

This paper cites Measuring Information Transfer in Neural Networks.

Compute-Optimal LLMs Provably Generalize Better With Scale Measuring Information Transfer in Neural Networks

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.312773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b67858b-2ad6-45d4-b272-117ad8f13fff · outbound

This paper cites Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach.

Compute-Optimal LLMs Provably Generalize Better With Scale Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-16T11:38:22.316432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b0430e10-3c59-4534-997b-f8613924f1d5 · inbound

A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search cites this paper.

A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search Compute-Optimal LLMs Provably Generalize Better With Scale

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:07:39.503440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.