Pith. sign in

Paper Citation Record · LEDGER

Probing Classifiers are Unreliable for Concept Removal and Detection

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2207.04153.

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

pith.paper-citation-record.v1
2207.04153 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 5 of 5 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 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:03:04.976946Z

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

5
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 d19b7b39-80d0-4f38-8f8b-677f8602b206 · inbound

Eliciting Latent Predictions from Transformers with the Tuned Lens cites this paper.

Eliciting Latent Predictions from Transformers with the Tuned Lens Probing Classifiers are Unreliable for Concept Removal and Detection

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-12T16:54:37.540135Z

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=2026-05-12T16:54:37.382049Z digest=sha256:bb5ebf635bbdf82026ef0ae812a778598b27380ad8909cdf0b0d34fd1b496871

Observation 3d487363-e1ce-434e-87ca-54783cf66f70 · inbound

Cross-Layer Discrete Concept Discovery for Interpreting Language Models cites this paper.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Probing Classifiers are Unreliable for Concept Removal and Detection

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T23:03:04.976946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:03:04.976946Z digest=sha256:47b1d21489f8bf7b29b780f482e389857e9b842f7e0d352a7c030ea3f7ea9378

Observation d022f78f-1bdd-40bd-bab5-cf65853f34b1 · inbound

Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles cites this paper.

Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles Probing Classifiers are Unreliable for Concept Removal and Detection

Reference 28

Resolution
metadata mismatch
arxiv_id, observed 2026-06-27T10:00:48.817125Z

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=2026-06-27T09:59:03.180341Z digest=sha256:c35702d90191fefd5940585d18912648e130560557ab554a11e2e2ee2eb28a08

Observation 5ebd3c60-7dae-440a-9a76-17e57dcf4ea7 · inbound

The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators cites this paper.

The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators Probing Classifiers are Unreliable for Concept Removal and Detection

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-02T07:09:31.632558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T07:09:31.632558Z digest=sha256:425b3bc182b7c6192d3c9de6c4d60d79b73304e61d8223e2bf7f077157a02b45

Observation 3e583314-e910-473e-a8c4-c3e0e2a670ce · inbound

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations cites this paper.

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations Probing Classifiers are Unreliable for Concept Removal and Detection

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-31T11:25:39.465818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T11:25:39.465818Z digest=sha256:8e9e12db293487a344c01c9fd80c54a4b976879674939f1eba132e56510527b5