Paper Citation Record · LEDGER

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

As of 24 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2404.07129.

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

pith.paper-citation-record.v1
2404.07129 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:47:07.742026Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-11T01:27:45.952692Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation eb54ad68-6d35-497b-adf4-12d5912b13ab · inbound

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit cites this paper.

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:28.407980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578cedac-9ff3-42d9-8978-b4f9c2846a8c · inbound

Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training cites this paper.

Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T17:06:43.982696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb5ffa12-f980-4474-b14d-ee50c8e0538a · inbound

Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation cites this paper.

Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T21:47:07.742026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfdb1959-86f5-4a9e-b95e-4c2f14f28bc5 · inbound

Mechanistic Interpretability of GPT-like Models on Summarization Tasks cites this paper.

Mechanistic Interpretability of GPT-like Models on Summarization Tasks What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:08.929374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a60ea88-84aa-4e0c-a9dc-f49d81c173ac · inbound

Relational reasoning and inductive bias in transformers and large language models cites this paper.

Relational reasoning and inductive bias in transformers and large language models What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:32:17.050874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8ce48db4-0054-42b8-ace2-9dd85ae16bd8 · inbound

Distinct Computations Emerge From Compositional Curricula in In-Context Learning cites this paper.

Distinct Computations Emerge From Compositional Curricula in In-Context Learning What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:58.280519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3858bb7e-c93c-418b-9313-39e21e7e98a3 · inbound

In-Context Learning Strategies Emerge Rationally cites this paper.

In-Context Learning Strategies Emerge Rationally What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T19:07:53.554879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 378ca455-c69c-4de8-a2f6-fb87c687111f · inbound

Soft Head Selection for Injecting ICL-Derived Task Embeddings cites this paper.

Soft Head Selection for Injecting ICL-Derived Task Embeddings What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T02:41:59.699451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7466d26f-5644-4496-aad6-24b6875a03e5 · inbound

Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis cites this paper.

Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T13:31:25.456593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 83dd8c64-a512-42d1-aec6-10b9c5c6d6ee · inbound

Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks cites this paper.

Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.169774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 62760610-ed8c-4e69-9414-07a417f764f0 · inbound

Belief or Circuitry? Causal Evidence for In-Context Graph Learning cites this paper.

Belief or Circuitry? Causal Evidence for In-Context Graph Learning What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:41:23.948708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a8d06ce-8e04-4865-a60d-d17f2a61e67d · inbound

Pretraining Curricula Enable Selective Fine-tuning cites this paper.

Pretraining Curricula Enable Selective Fine-tuning What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-11T12:36:24.747752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f99d38-a991-4329-8b16-884da7cfc69b · inbound

Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention cites this paper.

Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-07-11T01:27:45.979483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d43f212d-0589-46af-8853-0a3dde432882 · inbound

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning cites this paper.

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T15:06:18.093603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 754e5f61-90a1-4e01-9a12-dd61ba3d9f87 · inbound

When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL cites this paper.

When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T12:25:20.546289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.