# Understanding Generalization and Forgetting in In-Context Continual Learning

ORID `68AMoK2YNk` · **claim-faithful** repair 2026-07-27T19:05:50.659530+00:00

Paper-style claim pages with **inline numbers** and linked `evidence/` artifacts.

## Claims

- [Claim 1: 01-decomposes-task-t-prediction-error-irreducible](./01-decomposes-task-t-prediction-error-irreducible/) — VERIFIED (2/2)
- [Claim 2: 02-forgetting-arises-attention-reweighting-past](./02-forgetting-arises-attention-reweighting-past/) — VERIFIED (2/2)
- [Claim 3: 03-theory-predicts-non-monotonic-error-curves](./03-theory-predicts-non-monotonic-error-curves/) — VERIFIED (2/2)
- [Claim 4: 04-mean-misalignment-interference-persists-regardle](./04-mean-misalignment-interference-persists-regardle/) — VERIFIED (2/2)
- [Claim 5: 05-experiments-gpt-2-architectures-confirm-predicte](./05-experiments-gpt-2-architectures-confirm-predicte/) — VERIFIED (2/2)
- [Conclusion](./conclusion/)

## Artifacts

- [`evidence/claim_1.json`](../evidence/claim_1.json)
- [`evidence/claim_2.json`](../evidence/claim_2.json)
- [`evidence/claim_3.json`](../evidence/claim_3.json)
- [`evidence/claim_4.json`](../evidence/claim_4.json)
- [`evidence/claim_5.json`](../evidence/claim_5.json)