Paper Citation Record · LEDGER

Which Attention Heads Matter for In-Context Learning?

As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2502.14010.

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

pith.paper-citation-record.v1
2502.14010 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 2026-08-21T06:32:19.484+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:07:53.551197Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation b6463463-55d7-4be2-8ef9-945f69528613 · inbound

The broader spectrum of in-context learning cites this paper.

The broader spectrum of in-context learning Which Attention Heads Matter for In-Context Learning?

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-11T22:10:23.055200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd7f5f44-fb68-4b82-9977-e6950c7382dd · inbound

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

Distinct Computations Emerge From Compositional Curricula in In-Context Learning Which Attention Heads Matter for In-Context Learning?

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:59.663314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c73ad69b-f4bd-4f2a-bc6d-13fb8007afbb · inbound

In-Context Learning Strategies Emerge Rationally cites this paper.

In-Context Learning Strategies Emerge Rationally Which Attention Heads Matter for In-Context Learning?

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T19:07:53.551197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 559f2c11-27d4-4467-990f-fef5903a6315 · inbound

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation cites this paper.

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation Which Attention Heads Matter for In-Context Learning?

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T05:00:04.950853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 926e1f80-5ad7-4062-b523-88bd109d9233 · 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 Which Attention Heads Matter for In-Context Learning?

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:31:25.452593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 027fbc6e-dc89-4746-bcf1-e574d0b49cbf · inbound

Predicting the Emergence of Induction Heads in Language Model Pretraining cites this paper.

Predicting the Emergence of Induction Heads in Language Model Pretraining Which Attention Heads Matter for In-Context Learning?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T21:06:40.820193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cfbbeb3-fcd9-4dfd-8207-3ef371a7d86d · inbound

MIDUS: Memory-Infused Depth Up-Scaling cites this paper.

MIDUS: Memory-Infused Depth Up-Scaling Which Attention Heads Matter for In-Context Learning?

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:03:36.145951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c562e1a4-b940-4fcc-9993-e97ba7558062 · inbound

Compressed Sensing for Capability Localization in Large Language Models cites this paper.

Compressed Sensing for Capability Localization in Large Language Models Which Attention Heads Matter for In-Context Learning?

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T01:00:44.265889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af989d11-bc32-491e-a231-28d5f18cdc2b · inbound

When Context Sticks: Studying Interference in In-Context Learning cites this paper.

When Context Sticks: Studying Interference in In-Context Learning Which Attention Heads Matter for In-Context Learning?

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:36:09.515952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9a9112a7-f93c-4f42-8657-59c7aab3a662 · inbound

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior cites this paper.

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior Which Attention Heads Matter for In-Context Learning?

Reference 231

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T17:16:06.577442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f0849acc-6ddb-4948-a382-989a0e96e6ae · inbound

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning cites this paper.

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning Which Attention Heads Matter for In-Context Learning?

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-21T05:33:58.583417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 081c2371-be90-4599-9a20-a7abffd78315 · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Which Attention Heads Matter for In-Context Learning?

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-28T23:32:46.694055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 501bb876-5bfa-48af-bce6-6105dbbc89a6 · inbound

Explaining Attention with Program Synthesis cites this paper.

Explaining Attention with Program Synthesis Which Attention Heads Matter for In-Context Learning?

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:59:20.999931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4dc3b032-f102-43d7-ab5f-642a70b5b295 · inbound

Explaining Attention with Program Synthesis cites this paper.

Explaining Attention with Program Synthesis Which Attention Heads Matter for In-Context Learning?

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-30T12:04:39.194166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2f9276c2-1721-4d88-bea3-3c653ebbe4fe · inbound

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference cites this paper.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference Which Attention Heads Matter for In-Context Learning?

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.030660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.