Paper Citation Record · LEDGER

LEACE: Perfect linear concept erasure in closed form

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2306.03819.

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

pith.paper-citation-record.v1
2306.03819 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 16 of 16 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 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:52:52.950611Z

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

12
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 d39bb665-c618-4e06-9f2f-f859d173b574 · inbound

An Overview of Catastrophic AI Risks cites this paper.

An Overview of Catastrophic AI Risks LEACE: Perfect linear concept erasure in closed form

Reference 140

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:03:46.746111Z

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 2ffa5dd3-d5bc-4afd-bcbb-7294553df07c · inbound

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning cites this paper.

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning LEACE: Perfect linear concept erasure in closed form

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:33.812883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec0d3acd-6ace-44b5-988d-1e77b118b5ba · inbound

Converting MLPs into Polynomials in Closed Form cites this paper.

Converting MLPs into Polynomials in Closed Form LEACE: Perfect linear concept erasure in closed form

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T16:58:44.682073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6500d2cf-fa76-4ef8-a509-2a56279540ed · inbound

Slowing Learning by Erasing Simple Features cites this paper.

Slowing Learning by Erasing Simple Features LEACE: Perfect linear concept erasure in closed form

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-09T11:04:16.994820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cd5cc21-d94e-493f-b0a9-21c65b8f9e13 · inbound

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation cites this paper.

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation LEACE: Perfect linear concept erasure in closed form

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T04:52:52.950611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08b24cfc-1d9b-410a-b678-59098997a30a · inbound

Improved Representation Steering for Language Models cites this paper.

Improved Representation Steering for Language Models LEACE: Perfect linear concept erasure in closed form

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:51:27.766075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c720e652-a397-4707-a2d1-f1d602e33144 · inbound

Convergent Linear Representations of Emergent Misalignment cites this paper.

Convergent Linear Representations of Emergent Misalignment LEACE: Perfect linear concept erasure in closed form

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:24.652705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f38fc1-eb3a-4054-a0b6-42b6aaeb3f68 · inbound

Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis cites this paper.

Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis LEACE: Perfect linear concept erasure in closed form

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:16:08.256966Z

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 9ffaceb2-324d-48be-9aea-def866caef62 · inbound

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes cites this paper.

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes LEACE: Perfect linear concept erasure in closed form

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:31:10.190390Z

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 7d3d229c-e8f0-4ea3-8bbb-50c94a935f53 · inbound

The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans cites this paper.

The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans LEACE: Perfect linear concept erasure in closed form

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:26:26.075959Z

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 7b84c565-22da-4f60-804f-aadaa4caf94c · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces LEACE: Perfect linear concept erasure in closed form

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:17:54.733815Z

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 5e531d59-5bee-41c0-bf84-656182f13d29 · inbound

Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol cites this paper.

Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol LEACE: Perfect linear concept erasure in closed form

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T14:14:45.907870Z

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 7bd0d6b9-00e2-407b-9da0-aa69957cd81b · inbound

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

Emergent Misalignment Recruits a Pre-existing Persona Subspace LEACE: Perfect linear concept erasure in closed form

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:02.347185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6301a38-3151-4073-b727-c38faf2c484b · inbound

Emergent Latent-State Computation under Stochastic Volatility cites this paper.

Emergent Latent-State Computation under Stochastic Volatility LEACE: Perfect linear concept erasure in closed form

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T02:27:04.697404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32bd7989-6eb8-4ce8-90b7-87a43689a920 · inbound

The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text cites this paper.

The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text LEACE: Perfect linear concept erasure in closed form

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T00:17:05.512768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6dc615d-23df-4554-8970-f4f533e86c09 · inbound

ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders cites this paper.

ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders LEACE: Perfect linear concept erasure in closed form

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T07:58:31.124365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.