Pith. sign in

Paper Citation Record · LEDGER

Successor Heads: Recurring, Interpretable Attention Heads In The Wild

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 8 inbound Pith citation observations for arXiv:2312.09230.

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

pith.paper-citation-record.v1
2312.09230 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:31:59.801158Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T07:06:44.476515Z

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 46b404c0-1b8e-4257-9633-5cfae82e5e95 · inbound

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models cites this paper.

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-13T13:15:10.721813Z

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.

source=arxiv_source observed=2026-05-13T13:15:10.632115Z digest=sha256:0b610754ffb86299d2044a855280a75397cb0fd4207fd4ee19c162f37afaf7f2

Observation 56032f7f-3a9f-4bf5-8f60-5a264f06f9f6 · inbound

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation cites this paper.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T17:31:59.801158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:31:59.801158Z digest=sha256:a478ff67ef5e69eb5f9d065c487cefe84017ccaa00fbfd17c29ed0c58da5fef9

Observation 28b19002-e07b-47b1-9546-a01bdb3afaee · inbound

On Mechanistic Circuits for Extractive Question-Answering cites this paper.

On Mechanistic Circuits for Extractive Question-Answering Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-08T11:01:28.865958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:01:28.865958Z digest=sha256:91825dddc2d3113c7ea24865ed712e15615c3277c943ac4e3ae23df59edc331e

Observation ff19b961-2c6c-4c75-a2a8-7de80ebf4151 · inbound

To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems cites this paper.

To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-05-19T11:32:17.224568Z

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.

source=pdf_text observed=2026-05-19T11:30:47.877793Z digest=sha256:deee2d591c7046d3958fe41946c3197f9b6c329ca4e8c17c894a7af7d849cb01

Observation f77a6226-41ca-4b14-be6c-f912467957cc · inbound

Modular Arithmetic: Language Models Solve Math Digit by Digit cites this paper.

Modular Arithmetic: Language Models Solve Math Digit by Digit Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-06T05:02:52.940577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T05:02:52.940577Z digest=sha256:a9a494d711185143fc1d22e7c408a27c86756f7dd9c36f51953b5832b6503ddd

Observation 8a1ef151-094b-49c3-b881-e3e8c7075baa · inbound

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation cites this paper.

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 2010

Resolution
unresolved
no resolver link, observed 2026-08-05T17:16:33.052383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T17:16:33.052383Z digest=sha256:c908948dcc0d2af210b2436b5f33aad9a5334fcab747f0f7298cf25789b356a0

Observation bc5c4d12-15df-4b71-9025-a1d550f1ed7e · inbound

Model Science: getting serious about verification, explanation and control of AI systems cites this paper.

Model Science: getting serious about verification, explanation and control of AI systems Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-05T15:17:08.581962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T15:17:08.581962Z digest=sha256:a6a4c589176567b433e111996f342243ebbdcd82657cc23323bb2f2b47df5984

Observation 62583b8d-f0b8-4d7a-9556-e81f18d18646 · inbound

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models cites this paper.

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Reference 10

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T07:06:44.478312Z

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.

source=arxiv_source observed=2026-06-28T07:07:58.170765Z digest=sha256:34017b70c4fdbc8b379a6e2f778871e9b3073cb77eb0deda6e2d879c79d16871