Pith. sign in

Paper Citation Record · LEDGER

Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2410.02984.

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

pith.paper-citation-record.v1
2410.02984 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 2026-08-07T06:34:17.273281+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:48:39.266827Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T21:10:09.070496Z

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 33004008-74e1-4aac-af6d-2d62d86b86e2 · inbound

Stochastic Parameter Decomposition cites this paper.

Stochastic Parameter Decomposition Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T22:48:39.266827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T22:48:39.266827Z digest=sha256:2dc65737e230b2119d18e38b1496c7aadb80ae26ea0b793f75949f66bbfc2ecc

Observation d7f5f323-49dc-4ee7-92e7-77e61ff84f6d · inbound

From Global to Local: A Scalable Benchmark for Local Posterior Sampling cites this paper.

From Global to Local: A Scalable Benchmark for Local Posterior Sampling Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-06T12:50:59.050476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:50:59.050476Z digest=sha256:a0f9b5b6bf8378089cef2722726660598a6285eba53afaf8fbed76fe6f1157a5

Observation 8aa27789-5963-4c15-96fa-27fd2cdc90ca · inbound

Embryology of a Language Model cites this paper.

Embryology of a Language Model Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T10:16:49.978359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T10:16:49.978359Z digest=sha256:ea28809922ec99e3412cb1f142653c6d6c9e1460410eba0870a4ac0f6d868a65

Observation 81aed736-beff-4e20-b28b-0aea58b30eba · inbound

Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding cites this paper.

Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-18T13:21:24.236551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-05-18T13:17:57.627009Z digest=sha256:5a0b4d6a891ea1ee1123aa2075362d7dbd8315d935fe99f6822349a972334648

Observation 3b4f0e60-d96c-465c-8fc7-13da0cf08f9e · inbound

Specialization of softmax attention heads: insights from the high-dimensional single-location model cites this paper.

Specialization of softmax attention heads: insights from the high-dimensional single-location model Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T19:04:54.409550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T19:04:54.409550Z digest=sha256:0f5534059357a59a65decb740739daad76d552b8adaaeaac9401ba5eafd9840b

Observation 7d472f3f-4403-43d0-a6a4-db97f15b5885 · inbound

Mechanistic Anomaly Detection via Functional Attribution cites this paper.

Mechanistic Anomaly Detection via Functional Attribution Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 68

Resolution
verified exact
arxiv_id, observed 2026-05-11T12:46:10.121385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-05-10T03:00:17.876145Z digest=sha256:42bdceafd31555015f49d7624b5a9f3ca7f4a41bdb57f47058bc62f7390104bb

Observation ea58d5ce-250c-4df5-8f60-c970f3adc259 · inbound

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning cites this paper.

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:55:54.503334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-05-11T02:09:43.387814Z digest=sha256:7f3dc8bf1b2ea0fb52c27cb2b1798188f5e6ebbaee7a77c3bfb0af167fe283b0

Observation 41a5833a-f301-413c-8ac8-baecf2fb57a5 · inbound

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability cites this paper.

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 29

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T03:19:43.657725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-05-15T03:17:22.217041Z digest=sha256:cc9bdd392ad8327e79e9cf8944cd85e7057c36ea4c730b3aebdb12f7ff53b4a0

Observation e9068c25-6c64-436d-8038-70d0f542fdd0 · inbound

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics cites this paper.

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-21T07:34:02.937838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-05-21T07:30:07.287938Z digest=sha256:93fda30b0c4d6baa5cf12d2e0f9b83a11913f45d1768465584ccb4fc11affd93

Observation b49a05dc-f021-4ecd-aec7-f24ff786fae2 · inbound

Dead Directions: Geometric Singular Learning cites this paper.

Dead Directions: Geometric Singular Learning Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 39

Resolution
verified exact
arxiv_id, observed 2026-07-02T11:36:55.227766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-06-28T03:20:09.365073Z digest=sha256:3b4e910799889388b12589d28809fc979c1fe84f526b6a2ae2c421544c06f3b1

Observation def571b0-e0aa-4c99-a909-54116d57e554 · inbound

Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale cites this paper.

Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 49

Resolution
verified exact
arxiv_id, observed 2026-07-04T00:29:15.257929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-06-26T21:14:11.815522Z digest=sha256:b42ed9b107e0eadaecf98691f00babd63ec985e5150a1067297732b8168ba3dc

Observation 566917a8-6911-44d8-9be7-a5b907499fd2 · inbound

Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity cites this paper.

Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-07-04T06:19:38.228473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-06-26T14:36:17.793710Z digest=sha256:f9617f86ced11525da5590b22d8d916c5a1370fd6ee529a5114e1f55081bf5e8

Observation 0ffdcc8c-94e7-496c-8a3c-1d23243df397 · inbound

Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining cites this paper.

Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 41

Resolution
verified exact
arxiv_id, observed 2026-07-04T21:10:09.072092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-06-25T19:04:11.976747Z digest=sha256:0a87c74ae425cad7506fd122e02e023546ab3323cb3e4605451803dbaf2fd34e

Observation 9a7c1848-6b5d-47e4-9d88-c7251d0b2870 · inbound

Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment cites this paper.

Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-07-02T15:57:06.355684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-07-02T15:56:11.362639Z digest=sha256:2717358310f5395c1a9c942499b019dedf678efb93f23f3509063539eecd9f92

Observation 4a56f6e0-6378-4f6a-bccd-d4bd8e06aab9 · inbound

Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.

Emergent Misalignment Recruits a Pre-existing Persona Subspace Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

Reference 220

Resolution
unresolved
no resolver link, observed 2026-08-01T07:46:23.736421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T07:46:23.736421Z digest=sha256:92dc335c3f9914749cf75c3130e533aff164479320e9ff94f197e0c5ad017903