Paper Citation Record · LEDGER

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks

As of 19 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2505.12268.

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

pith.paper-citation-record.v1
2505.12268 v2

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:41:57.857103Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy3
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a5082a35-1917-4b11-9bee-9eba6da766fa · outbound

This paper cites What does bert look at? an analysis of bert’s attention.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks What does bert look at? an analysis of bert’s attention

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:41:58.720514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 31e54323-2bdd-4f38-8adf-3d2c38cb5fb2 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.713019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2758c388-4eea-4f35-bccd-c27306f92bc6 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Scaling and evaluating sparse autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.735467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a80de9-8fb3-432b-8930-313ba78f6b85 · outbound

This paper cites Automatically Identifying Local and Global Circuits with Linear Computation Graphs.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Automatically Identifying Local and Global Circuits with Linear Computation Graphs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.746262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97258de6-1dd7-4a72-bca0-e374b93edbb0 · outbound

This paper cites A structural probe for finding syntax in word representations.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks A structural probe for finding syntax in word representations

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:41:58.658711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8b18c6d1-e4d3-41ad-83a0-82e88774668c · outbound

This paper cites Language Models Use Trigonometry to Do Addition.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Language Models Use Trigonometry to Do Addition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.767445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffdf4d0-d5bb-4961-ac75-ea6d1f1ead9f · outbound

This paper cites Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T20:41:58.347588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 440a097c-656c-4f0f-a9a0-aa3c490c71ba · outbound

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

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.783451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51320bff-1c9a-453c-981e-44cee6b1c88d · outbound

This paper cites A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.806134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8059930-f293-4912-8a85-531183a2883b · outbound

This paper cites Planning in a recurrent neural network that plays Sokoban.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Planning in a recurrent neural network that plays Sokoban

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.812580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a874f307-8349-43ce-af75-229ecd86002e · outbound

This paper cites Greedy SLIM: A SLIM-Based Approach For Preference Elicitation.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Greedy SLIM: A SLIM-Based Approach For Preference Elicitation

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T20:41:58.180758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0a511791-e9b3-46f4-a480-65a6d0a544fc · outbound

This paper cites Do Large Language Models Latently Perform Multi-Hop Reasoning?.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Do Large Language Models Latently Perform Multi-Hop Reasoning?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.829613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f918cea-6a9c-42de-bfe7-3316fd7c7214 · outbound

This paper cites Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.837990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd8144b-9469-465b-9e17-ea312c87ba26 · outbound

This paper cites The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.847407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23e470d9-494f-4ca0-847e-47ff2cb4e4a5 · outbound

This paper cites Pre-trained Large Language Models Use Fourier Features to Compute Addition.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Pre-trained Large Language Models Use Fourier Features to Compute Addition

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.857103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d84e79-42d6-4a6c-9b71-27d15d99acab · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Training Verifiers to Solve Math Word Problems

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.707058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5942f11e-34e8-4f12-9e3c-73ebb11e926f · outbound

This paper cites Andrew Stolfo, Atticus Geiger, David Friedman, and Vivek Srikumar.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Andrew Stolfo, Atticus Geiger, David Friedman, and Vivek Srikumar

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.798063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb3afd0-cdf1-4716-93ec-40fce452e4c0 · outbound

This paper cites Lucy Gao, Lachlan Reynolds, Neel Nanda, and Chris Olah.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Lucy Gao, Lachlan Reynolds, Neel Nanda, and Chris Olah

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:41:58.685822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 831539e5-aef9-43d1-9f5a-1fa53e94a015 · outbound

This paper cites Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.678412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 050025f9-5eb3-4283-b2e6-1356f1c0b97d · outbound

This paper cites Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.669378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 051ef9ac-a2d4-4b48-a5ac-1d69ebca18c1 · outbound

This paper cites Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages.

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T20:41:57.686649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.