Decomposing Prediction Mechanisms for In-Context Recall | Paper Citation Record

Observation 5d63445b-9904-4aa1-9fcd-352603307b18 · outbound

This paper cites In-Context Language Learning: Architectures and Algorithms.

Decomposing Prediction Mechanisms for In-Context Recall In-Context Language Learning: Architectures and Algorithms

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.325633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b19d44-e34d-4448-a1b7-0f8fc71f69b8 · outbound

This paper cites Lepori, Jack Merullo, and Ellie Pavlick.

Decomposing Prediction Mechanisms for In-Context Recall Lepori, Jack Merullo, and Ellie Pavlick

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.391018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6d43768-d201-4cbb-9be7-612c124966d4 · outbound

This paper cites Zoology: Measuring and Improving Recall in Efficient Language Models.

Decomposing Prediction Mechanisms for In-Context Recall Zoology: Measuring and Improving Recall in Efficient Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.494240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5ac2633-72d9-4809-ba23-b5ac0b410e82 · outbound

This paper cites Copernicus, New York, NY , USA, 1996.

Decomposing Prediction Mechanisms for In-Context Recall Copernicus, New York, NY , USA, 1996

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.557374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207607ea-25dc-4828-8ae7-4bb8ce2d546f · outbound

This paper cites Beyond the imitation game: Quantifying and extrapolating the capabilities of language models.Transactions on Machine Learning Research, 2023.

Decomposing Prediction Mechanisms for In-Context Recall Beyond the imitation game: Quantifying and extrapolating the capabilities of language models.Transactions on Machine Learning Research, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.637617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 032bf900-263b-4253-9a51-6e01fb661c56 · outbound

This paper cites Finding transformer circuits with edge pruning.

Decomposing Prediction Mechanisms for In-Context Recall Finding transformer circuits with edge pruning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.729232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78db4f16-32ca-47de-b375-2d4c0c16fbb0 · outbound

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

Decomposing Prediction Mechanisms for In-Context Recall Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.830622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db2150c0-0f3e-41b5-8df8-7b6ffbd542bb · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.922775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f2873f2-e3ae-4c09-a79f-3e64fb34b23e · outbound

This paper cites Toward understanding in-context vs.

Decomposing Prediction Mechanisms for In-Context Recall Toward understanding in-context vs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:47.990675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8c0232-67ae-42da-9f40-579c5dce449a · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.058830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 155da576-b9f3-48bd-9e5f-055be0e4a8a8 · outbound

This paper cites Sudden drops in the loss: Syntax acquisition, phase transitions, and simplicity bias in MLMs.

Decomposing Prediction Mechanisms for In-Context Recall Sudden drops in the loss: Syntax acquisition, phase transitions, and simplicity bias in MLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.125248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b051e9bc-f5c2-4236-8f43-17bc5f1db24e · outbound

This paper cites Quantifying semantic emergence in language models, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Quantifying semantic emergence in language models, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.689610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bc162cb3-65db-437b-a29f-d57d543a9333 · outbound

This paper cites Dynamical versus bayesian phase transitions in a toy model of superposition, 2023.

Decomposing Prediction Mechanisms for In-Context Recall Dynamical versus bayesian phase transitions in a toy model of superposition, 2023

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.675192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9ace98a6-1810-4e4e-b52f-24edb86128f2 · outbound

This paper cites Unifying Grokking and Double Descent.

Decomposing Prediction Mechanisms for In-Context Recall Unifying Grokking and Double Descent

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.356869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36919971-e03f-4af6-87ec-6f6dbf4a9630 · outbound

This paper cites Can transformers learn optimal filtering for unknown systems?IEEE Control Systems Letters, 7:3525–3530, 2023.

Decomposing Prediction Mechanisms for In-Context Recall Can transformers learn optimal filtering for unknown systems?IEEE Control Systems Letters, 7:3525–3530, 2023

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.660506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d5873c6d-c0ee-4533-a4bd-ff4e6cce04e3 · outbound

This paper cites Understanding emergent abilities of language models from the loss perspective, 2025.

Decomposing Prediction Mechanisms for In-Context Recall Understanding emergent abilities of language models from the loss perspective, 2025

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.645956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6f0fa652-2942-45fe-a97e-2280ce290262 · outbound

This paper cites The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains.

Decomposing Prediction Mechanisms for In-Context Recall The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.557237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee229cd8-fb24-4b55-9fe6-b5c160e377e9 · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread,.

Decomposing Prediction Mechanisms for In-Context Recall A mathematical framework for transformer circuits.Transformer Circuits Thread,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.634788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7461706-7e55-4ca8-9e43-a9e4ee485eb2 · outbound

This paper cites Predictability and surprise in large generative models.

Decomposing Prediction Mechanisms for In-Context Recall Predictability and surprise in large generative models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.611107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f523d299-edc4-48a9-ade2-efcce5a27bf7 · 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.

Decomposing Prediction Mechanisms for In-Context Recall What can transformers learn in-context? a case study of simple function classes.Advances in Neural Information Processing Systems, 35:30583–30598, 2022

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.874830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e27c69-de1b-4d9d-81d4-70126a5b76c8 · outbound

This paper cites OLMo: Accelerating the Science of Language Models.

Decomposing Prediction Mechanisms for In-Context Recall OLMo: Accelerating the Science of Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.954246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c11acdc7-b915-4c30-bbee-d21ed541daf4 · outbound

This paper cites Grokking modular arithmetic.

Decomposing Prediction Mechanisms for In-Context Recall Grokking modular arithmetic

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:49.031244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d6cc3ad-fdba-435e-bbe0-8ec343865c1a · outbound

This paper cites Loss landscape degeneracy drives stagewise development in transformers, 2025.

Decomposing Prediction Mechanisms for In-Context Recall Loss landscape degeneracy drives stagewise development in transformers, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.586092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fd601a35-8b4c-4b53-a661-43ef27000f66 · outbound

This paper cites Neural networks and physical systems with emergent collective computational abilities.Proceedings of the national academy of sciences, 79(8):2554–2558, 1982.

Decomposing Prediction Mechanisms for In-Context Recall Neural networks and physical systems with emergent collective computational abilities.Proceedings of the national academy of sciences, 79(8):2554–2558, 1982

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:49.187011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fbf382b-11c6-4e9f-bcfa-8a1bcefa9927 · outbound

This paper cites Task descriptors help transformers learn linear models in-context.

Decomposing Prediction Mechanisms for In-Context Recall Task descriptors help transformers learn linear models in-context

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.560528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7ff2b510-b71f-43d7-94ff-6aa2798a8dae · outbound

This paper cites Deep networks always grok and here is why.

Decomposing Prediction Mechanisms for In-Context Recall Deep networks always grok and here is why

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.544878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 67e4b03f-617a-4dc8-b0a4-ce4bd50f7f8e · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-06T20:57:51.530373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5780ac73-d04a-4e0c-b3b4-8316f3714c72 · outbound

This paper cites Grokking as the transition from lazy to rich training dynamics.

Decomposing Prediction Mechanisms for In-Context Recall Grokking as the transition from lazy to rich training dynamics

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.515532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1aa3af2f-3150-4b30-a59a-66594e8a73f9 · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-06T20:57:51.499994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64c6aff3-b30d-44fe-abd8-6fadb4733a06 · outbound

This paper cites The local learning coefficient: A singularity-aware complexity measure, 2024.

Decomposing Prediction Mechanisms for In-Context Recall The local learning coefficient: A singularity-aware complexity measure, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.484652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cca60b8a-8980-4b77-abc3-e7d778eb3db3 · outbound

This paper cites Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling.

Decomposing Prediction Mechanisms for In-Context Recall Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-06T20:57:50.729788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f77a2e13-8aeb-4532-8a80-ea132a00d750 · outbound

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

Decomposing Prediction Mechanisms for In-Context Recall Trans- formers as algorithms: Generalization and stability in in-context learning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.470598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 99bfa400-d578-497d-bea8-ea8c3d4b4f5e · outbound

This paper cites Dual operating modes of in-context learning, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Dual operating modes of in-context learning, 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.456102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f38d062f-5859-480d-8a95-86e6c878fafc · outbound

This paper cites Can transformers solve least squares to high precision? InICML 2024 Workshop on In-Context Learning, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Can transformers solve least squares to high precision? InICML 2024 Workshop on In-Context Learning, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.441982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7b828d0f-6eb3-461a-b0e5-a0942822f9e1 · outbound

This paper cites Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang.

Decomposing Prediction Mechanisms for In-Context Recall Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.201250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671c5f59-d0c5-47c4-ba43-fc4270979382 · outbound

This paper cites Omnigrok: Grokking beyond algorithmic data.

Decomposing Prediction Mechanisms for In-Context Recall Omnigrok: Grokking beyond algorithmic data

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.418824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2688f4e1-93c3-4562-ba48-a348e8927a75 · outbound

This paper cites Decoupled weight decay regularization, 2019.

Decomposing Prediction Mechanisms for In-Context Recall Decoupled weight decay regularization, 2019

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.327309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e1679c7-fd4d-487e-9ea8-b2e1e801596d · outbound

This paper cites Are Emergent Abilities in Large Language Models just In-Context Learning?.

Decomposing Prediction Mechanisms for In-Context Recall Are Emergent Abilities in Large Language Models just In-Context Learning?

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.362140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ddb44b2-94e3-4b9f-b5d3-04c049609a5a · outbound

This paper cites Dick, and Hidenori Tanaka.

Decomposing Prediction Mechanisms for In-Context Recall Dick, and Hidenori Tanaka

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.394536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation af9cca3c-f0ec-4dc1-9f81-3963a84a4100 · outbound

This paper cites Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking.

Decomposing Prediction Mechanisms for In-Context Recall Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.370208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb2a53ad-8667-469a-98be-b25573be7a5c · outbound

This paper cites A practical bayesian framework for backpropagation networks.Neural computation, 4(3):448–472, 1992.

Decomposing Prediction Mechanisms for In-Context Recall A practical bayesian framework for backpropagation networks.Neural computation, 4(3):448–472, 1992

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.380244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0f1e8a9f-4ec7-4a60-9e96-f23fc3968f19 · outbound

This paper cites Exact learning dynamics of in-context learning in linear transformers and its application to non-linear transformers, 2025.

Decomposing Prediction Mechanisms for In-Context Recall Exact learning dynamics of in-context learning in linear transformers and its application to non-linear transformers, 2025

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.365506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b811f6a1-233f-4b67-9aa6-3e190e35d328 · outbound

This paper cites Emergence in non-neural models: grokking modular arithmetic via average gradient outer product.

Decomposing Prediction Mechanisms for In-Context Recall Emergence in non-neural models: grokking modular arithmetic via average gradient outer product

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.352256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2e476f30-2f64-4823-8ab4-256fca7fa2b9 · outbound

This paper cites Hoffman, and David M.

Decomposing Prediction Mechanisms for In-Context Recall Hoffman, and David M

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.338471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 89ea9f58-4226-4de9-8aa3-64b1b117e973 · outbound

This paper cites How to generate random matrices from the classical compact groups.

Decomposing Prediction Mechanisms for In-Context Recall How to generate random matrices from the classical compact groups

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.391686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 000462f9-ae81-4b07-b946-d478a9b70acd · outbound

This paper cites The quantization model of neural scaling.Advances in Neural Information Processing Systems, 36, 2023.

Decomposing Prediction Mechanisms for In-Context Recall The quantization model of neural scaling.Advances in Neural Information Processing Systems, 36, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.396097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b818bee2-639b-4d05-9836-953ecb2326b9 · outbound

This paper cites Rethinking the role of demonstrations: What makes in-context learning work?, 2022.

Decomposing Prediction Mechanisms for In-Context Recall Rethinking the role of demonstrations: What makes in-context learning work?, 2022

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.314342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation de8c6695-0166-46fa-bb2c-b0af4bfa9530 · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-06T20:57:51.301004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 12f57399-d789-4112-9fbb-12097e4db8c2 · outbound

This paper cites Grokking mod- ular arithmetic can be explained by margin maximization.

Decomposing Prediction Mechanisms for In-Context Recall Grokking mod- ular arithmetic can be explained by margin maximization

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.286523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c4136913-72b4-4aa7-80dc-acff20b83f9c · outbound

This paper cites Transformers can do bayesian inference, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Transformers can do bayesian inference, 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.272974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4afa61df-3135-4f40-9fbe-3d2fc9b9d5c5 · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-06T20:57:51.260246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 39032d8a-d2b7-44af-8ad3-b2e3b7d80178 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Decomposing Prediction Mechanisms for In-Context Recall Progress measures for grokking via mechanistic interpretability

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.247422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5cba795c-5d46-425e-8f06-e0ed8037d815 · outbound

This paper cites Differential learning kinetics govern the transition from memorization to generalization during in-context learning, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Differential learning kinetics govern the transition from memorization to generalization during in-context learning, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.233720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dfae44a1-5038-4732-a3fd-6f2bae8a87f4 · outbound

This paper cites Lee, and Alberto Bietti.

Decomposing Prediction Mechanisms for In-Context Recall Lee, and Alberto Bietti

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.428875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc02881c-073f-4447-a58a-c6529843e325 · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-06T20:57:51.210591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 723e21ed-5bbb-494a-ba82-8819d30f6d07 · outbound

This paper cites In-context Learning and Induction Heads.

Decomposing Prediction Mechanisms for In-Context Recall In-context Learning and Induction Heads

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.436894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 804ec645-8b21-45a2-8494-2d2f930f556e · outbound

This paper cites What in-context learning "learns" in-context: Disentangling task recognition and task learning, 2023.

Decomposing Prediction Mechanisms for In-Context Recall What in-context learning "learns" in-context: Disentangling task recognition and task learning, 2023

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.198025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a31572cc-2f52-44f7-99eb-3f535e10d3d3 · outbound

This paper cites In-context learning through the bayesian prism, 2024.

Decomposing Prediction Mechanisms for In-Context Recall In-context learning through the bayesian prism, 2024

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.185916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 30793b95-aaa8-4e66-ab42-9d3ac3c85cb2 · outbound

This paper cites Competition dynamics shape algorithmic phases of in-context learning, 2025.

Decomposing Prediction Mechanisms for In-Context Recall Competition dynamics shape algorithmic phases of in-context learning, 2025

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.173103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 56e50786-2ff2-4886-9bf7-18a2bb1b7030 · outbound

This paper cites Gradient starvation: A learning proclivity in neural networks.Advances in Neural Information Processing Systems, 34:1256–1272, 2021.

Decomposing Prediction Mechanisms for In-Context Recall Gradient starvation: A learning proclivity in neural networks.Advances in Neural Information Processing Systems, 34:1256–1272, 2021

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.160478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1bd7c59a-1a78-4b51-b1df-733fd66ea5f2 · outbound

This paper cites Multi-scale feature learning dynamics: Insights for double descent.

Decomposing Prediction Mechanisms for In-Context Recall Multi-scale feature learning dynamics: Insights for double descent

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.146280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0cfea553-1a99-4ff6-9f62-f81d01c3d2a3 · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

Decomposing Prediction Mechanisms for In-Context Recall Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.459920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1333739d-8086-4ea3-b2b4-c1b15760c450 · outbound

This paper cites Grokking at the Edge of Numerical Stability.

Decomposing Prediction Mechanisms for In-Context Recall Grokking at the Edge of Numerical Stability

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.463997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0788a3e0-1ddb-4c08-8369-c2c6cdd85b21 · outbound

This paper cites Transformers on markov data: Constant depth suffices.

Decomposing Prediction Mechanisms for In-Context Recall Transformers on markov data: Constant depth suffices

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.131965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c138f444-e289-4a3a-955f-a983ca9ba18d · 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, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression.Advances in Neural Information Processing Systems, 36, 2024

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.119108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d8816f7d-d4f4-44ca-93a9-b11c684ea924 · outbound

This paper cites The mechanistic basis of data dependence and abrupt learning in an in-context classification task, 2023.

Decomposing Prediction Mechanisms for In-Context Recall The mechanistic basis of data dependence and abrupt learning in an in-context classification task, 2023

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.105229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3b117b78-3ca9-46d5-be1f-4c625d258c31 · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-06T20:57:51.092216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d0be3b76-8c60-4dca-9dfc-0f69584c4c0b · outbound

This paper cites Are emergent abilities of large language models a mirage?Advances in Neural Information Processing Systems, 36, 2024.

Decomposing Prediction Mechanisms for In-Context Recall Are emergent abilities of large language models a mirage?Advances in Neural Information Processing Systems, 36, 2024

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.079229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c0b2b5b6-35a6-4236-92a8-1a58e2b0ade3 · outbound

This paper cites I preliminaries.

Decomposing Prediction Mechanisms for In-Context Recall I preliminaries

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.064250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 242a903a-fc53-44cc-a146-c3c17f33ccab · outbound

This paper cites The pitfalls of simplicity bias in neural networks.Advances in Neural Information Processing Systems, 33:9573–9585, 2020.

Decomposing Prediction Mechanisms for In-Context Recall The pitfalls of simplicity bias in neural networks.Advances in Neural Information Processing Systems, 33:9573–9585, 2020

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.051341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9c6ec1f4-3189-431b-867b-8c21c43043e3 · outbound

This paper cites Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C.

Decomposing Prediction Mechanisms for In-Context Recall Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.037428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2c1c3dee-e0cc-4819-bf45-53af02abf929 · outbound

This paper cites Singh, Ted Moskovitz, Felix Hill, Stephanie C.

Decomposing Prediction Mechanisms for In-Context Recall Singh, Ted Moskovitz, Felix Hill, Stephanie C

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.024189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a103b708-0a07-4d13-bc18-0ea7a8e788ec · outbound

This paper cites The implicit bias of gradient descent on separable data.Journal of Machine Learning Research, 19:1–57, 2018.

Decomposing Prediction Mechanisms for In-Context Recall The implicit bias of gradient descent on separable data.Journal of Machine Learning Research, 19:1–57, 2018

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:51.010579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c891c0cf-7476-4b69-955f-2c8bae446104 · outbound

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

Decomposing Prediction Mechanisms for In-Context Recall Transformers learn in-context by gradient descent

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.508348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe94556-f4bf-4227-9d1b-a21d3519d5a1 · outbound

This paper cites Label words are anchors: An information flow perspective for understanding in-context learning, 2023.

Decomposing Prediction Mechanisms for In-Context Recall Label words are anchors: An information flow perspective for understanding in-context learning, 2023

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.988282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7d418978-8f03-473f-8a2a-27b221e519d0 · outbound

This paper cites Investigating the pre-training dynamics of in-context learning: Task recognition vs.

Decomposing Prediction Mechanisms for In-Context Recall Investigating the pre-training dynamics of in-context learning: Task recognition vs

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.975604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 31f1e21a-5422-4bd8-9538-0f6d41977210 · outbound

This paper cites Cambridge monographs on applied and computational mathematics ; 25.

Decomposing Prediction Mechanisms for In-Context Recall Cambridge monographs on applied and computational mathematics ; 25

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.962394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7f2b0d05-542c-44dd-9d49-b6bb9ca53394 · outbound

This paper cites Emergent abilities of large language models.Transactions on Machine Learning Research, 2022.

Decomposing Prediction Mechanisms for In-Context Recall Emergent abilities of large language models.Transactions on Machine Learning Research, 2022

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.523610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e7c1c8-f9d5-48f1-8ca4-3c063d7021c9 · outbound

This paper cites Symbol tuning improves in-context learning in language models.

Decomposing Prediction Mechanisms for In-Context Recall Symbol tuning improves in-context learning in language models

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.938971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c235e701-5b2f-423d-9b9b-ab38e5b64c8a · outbound

This paper cites Larger language models do in-context learning differently, 2023.

Decomposing Prediction Mechanisms for In-Context Recall Larger language models do in-context learning differently, 2023

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.924799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4f03d646-60e7-4d00-bb02-6a3de0a0c218 · outbound

This paper cites The learnability of in-context learning, 2023.

Decomposing Prediction Mechanisms for In-Context Recall The learnability of in-context learning, 2023

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.909234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 443613bf-e32b-4658-8855-fc8e5a97ae2c · outbound

This paper cites Bartlett.

Decomposing Prediction Mechanisms for In-Context Recall Bartlett

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.893332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9aa4c803-6d33-4dd4-81a1-bd1920753f32 · outbound

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

Decomposing Prediction Mechanisms for In-Context Recall An Explanation of In-context Learning as Implicit Bayesian Inference

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:50.542232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8626323f-a16e-49be-9356-71764c22750d · outbound

This paper cites Which attention heads matter for in-context learning?, 2025.

Decomposing Prediction Mechanisms for In-Context Recall Which attention heads matter for in-context learning?, 2025

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.879642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ed80c7c0-bf72-4ce1-9cc5-baa668260520 · outbound

This paper cites Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization.

Decomposing Prediction Mechanisms for In-Context Recall Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-08-06T20:57:50.607902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c3428b09-90c6-4d74-81e6-aecdb2189132 · outbound

This paper cites Singh, Peter E.

Decomposing Prediction Mechanisms for In-Context Recall Singh, Peter E

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:57:50.865767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e23d4f56-2c7b-436e-a12d-ccf86e2ee14d · outbound

This paper cites grokking.

Decomposing Prediction Mechanisms for In-Context Recall grokking

Reference 87

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T20:57:50.850211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7cf24358-5e8d-4b23-a0b3-ad11780b5920 · outbound

This paper cites tiny”, “small.

Decomposing Prediction Mechanisms for In-Context Recall tiny”, “small

Reference 89

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T20:57:50.836438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1d1e9eaf-2462-474c-ba00-9998e195de43 · outbound

This paper cites an unresolved cited work.

Decomposing Prediction Mechanisms for In-Context Recall Unresolved cited work

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T20:57:48.723869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers