Paper Citation Record · LEDGER

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity

As of 8 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2602.17743.

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

pith.paper-citation-record.v1
2602.17743 v2

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:19:25.000465Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e43a5379-88f1-4767-96c9-ec5a1bee1ced · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.145224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df79976d-786c-4099-9f57-a49e1a3d8b3d · outbound

This paper cites Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.230499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3024d273-a56e-45dc-a911-9098cffffad5 · outbound

This paper cites An Explanation of In-context Learning as Implicit Bayesian Inference.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity An Explanation of In-context Learning as Implicit Bayesian Inference

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.307467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 378fb731-d62e-46c1-9f5f-614ee7b68720 · outbound

This paper cites In-context learning is provably bayesian inference: A generalization theory for meta-learning.arXiv preprint arXiv:2510.10981, 2025.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity In-context learning is provably bayesian inference: A generalization theory for meta-learning.arXiv preprint arXiv:2510.10981, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.381339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad3919cb-52e5-4da8-aebc-177ed9aeacad · outbound

This paper cites Transformers learn in-context by gradient descent.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Transformers learn in-context by gradient descent

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.482123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46aef11-b7c3-47bf-b0d0-6ce4e92d58c5 · outbound

This paper cites Transformers learn to implement preconditioned gradient descent for in-context learning.Advances in Neural Information Processing Systems, 36:45614–45650, 2023.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Transformers learn to implement preconditioned gradient descent for in-context learning.Advances in Neural Information Processing Systems, 36:45614–45650, 2023

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.579367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c769a4bc-d07b-442c-908b-5837fa51655b · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.686038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd50ed31-c6ea-4eef-a5bf-343b9adbf7a5 · outbound

This paper cites Jailbroken: How does llm safety training fail?Advances in Neural Information Processing Systems, 36:80079–80110, 2023.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Jailbroken: How does llm safety training fail?Advances in Neural Information Processing Systems, 36:80079–80110, 2023

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.793582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8dddf92-1504-4676-8c36-e273aede687c · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.870827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554dd639-fa1a-4a66-b734-2a7c586f0e60 · outbound

This paper cites Optimal In-context Adaptivity and Distributional Robustness of Transformers.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Optimal In-context Adaptivity and Distributional Robustness of Transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:22.958702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46cc1d35-cf3f-4d3a-a030-5919ea97bc5e · outbound

This paper cites Certifying Some Distributional Robustness with Principled Adversarial Training.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Certifying Some Distributional Robustness with Principled Adversarial Training

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.064805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc867cc7-3193-4070-9cbc-e21070571ed0 · outbound

This paper cites A distributionally robust perspective on uncertainty quantification and chance constrained programming.Mathematical Programming, 151(1):35–62, 2015.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity A distributionally robust perspective on uncertainty quantification and chance constrained programming.Mathematical Programming, 151(1):35–62, 2015

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.163869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59a7d9f1-8e4b-4a14-a65d-fd2cf51ed0a8 · outbound

This paper cites What can transformers learn in-context? a case study of simple function classes.Advances in neural information processing systems, 35:30583–30598, 2022.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity What can transformers learn in-context? a case study of simple function classes.Advances in neural information processing systems, 35:30583–30598, 2022

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.274566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42928dde-37a8-4c4d-b1e8-35309ffc8c0d · outbound

This paper cites Transformers as statisticians: Provable in-context learning with in-context algorithm selection.Advances in neural information processing systems, 36:57125–57211, 2023.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Transformers as statisticians: Provable in-context learning with in-context algorithm selection.Advances in neural information processing systems, 36:57125–57211, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.376413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21fe781d-d9c1-428a-9a7c-70864dc70904 · outbound

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

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Transformers as algorithms: Generalization and stability in in-context learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.452948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e797193-9bca-4dee-a27f-c8e57dd96615 · outbound

This paper cites Pretraining task diversity and the emergence of non-bayesian in-context learning for regression.Advances in neural information processing systems, 36:14228– 14246, 2023.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Pretraining task diversity and the emergence of non-bayesian in-context learning for regression.Advances in neural information processing systems, 36:14228– 14246, 2023

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.526724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b37ec43a-b3c4-48f8-92cf-e6c039b372bf · outbound

This paper cites Piecewise linear regression via a difference of convex functions.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Piecewise linear regression via a difference of convex functions

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.617496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0ddc94-32f6-4b25-9546-cbc9bd32219e · outbound

This paper cites Finite-sample analysis of m-estimators using self-concordance.Electronic Journal of Statistics, 15:326–391, 2021.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Finite-sample analysis of m-estimators using self-concordance.Electronic Journal of Statistics, 15:326–391, 2021

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.725937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fd457b1-f9a9-4528-a7c7-f9761bf77bf4 · outbound

This paper cites What learning algorithm is in-context learning? Investigations with linear models.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity What learning algorithm is in-context learning? Investigations with linear models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.802187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2201271-7f22-4384-8742-54b34a4cdf71 · outbound

This paper cites Trained Transformers Learn Linear Models In-Context.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Trained Transformers Learn Linear Models In-Context

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:23.982015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41d126c2-40b3-470d-a99c-8309fd4456b4 · outbound

This paper cites Wasserstein distributionally robust optimization: Theory and applications in machine learning.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Wasserstein distributionally robust optimization: Theory and applications in machine learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:24.217308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28325ea6-3178-449a-b6fd-38b93767890a · outbound

This paper cites an unresolved cited work.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:24.369296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00a9756-9f51-4f64-a711-3cca25672556 · outbound

This paper cites an unresolved cited work.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:24.488775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e2cf2d5-0939-4918-86ed-93f0826426e8 · outbound

This paper cites Larger models (bigger m) are smoother, making them less sensitive to shifts.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Larger models (bigger m) are smoother, making them less sensitive to shifts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:24.722634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac8f255c-2c38-40fb-8ac7-64c95f8c3d0b · outbound

This paper cites an unresolved cited work.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:24.900156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a76e75d-7288-4392-bdde-6e9d07294aaf · outbound

This paper cites The p d/mand1/ √ Nscaling laws remain unchanged.

Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity The p d/mand1/ √ Nscaling laws remain unchanged

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T22:19:25.000465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.