Paper Citation Record · LEDGER

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

As of 4 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2602.10352.

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

pith.paper-citation-record.v1
2602.10352 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T01:14:59.660318Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T03:21:30.932283Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T07:26:26.034345Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ed057f1e-cdae-4fdf-bc73-325d66801d0c · outbound

This paper cites Tell me about.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Tell me about

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.647413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b8e4095-0c9a-4f18-875c-7f11a7526bd9 · outbound

This paper cites Factorials in combinatorics.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Factorials in combinatorics

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.718966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c2757a0-0aa2-470a-bc9b-89cf7b502842 · outbound

This paper cites Tell me about [topic].

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Tell me about [topic]

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:59.232649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d8b7aa-686f-4f73-8bfe-5733b9e62f8e · outbound

This paper cites Kissane, C., Krzyzanowski, R., Conmy, A., and Nanda, N.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Kissane, C., Krzyzanowski, R., Conmy, A., and Nanda, N

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-03T01:14:58.155823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c040916-a8f8-4b11-8907-acb2332be587 · outbound

This paper cites URL https://arxiv.org/abs/2511.08579.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs URL https://arxiv.org/abs/2511.08579

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.193388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d899097-a7a3-44c9-8a4f-950fb72b03c9 · outbound

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

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Do Large Language Models Latently Perform Multi-Hop Reasoning?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.578330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8939c515-2167-4bab-a24c-6d8969e8d3ea · outbound

This paper cites an unresolved cited work.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.986640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31dd630c-5491-4520-be02-7a8d9d450ca9 · outbound

This paper cites an unresolved cited work.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:59.086880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d03c27a0-fd53-43c6-a345-2f194bd66d8b · outbound

This paper cites an unresolved cited work.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:59.402782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f42e4a61-4db6-42d2-ba5e-24fb6d7322c6 · outbound

This paper cites Left Ginza.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Left Ginza

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:59.524167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a16c97a-6e99-4de5-ad89-23360f0470e7 · outbound

This paper cites reasoning.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:59.554865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b88c734-a6f3-4eb5-b072-919c81abb261 · outbound

This paper cites Tell me about [topic].

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Tell me about [topic]

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:59.572874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 692a6ed7-739b-47f8-928b-f18a41d9c38d · outbound

This paper cites Lindsey, J.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Lindsey, J

Reference 147

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.385110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a3cf3b-d41d-4ac6-aeed-d48ea1255d0c · outbound

This paper cites Towards General Text Embeddings with Multi-stage Contrastive Learning.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Towards General Text Embeddings with Multi-stage Contrastive Learning

Reference 353

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.256692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feddd9b1-463e-42c8-acff-10c4c15954d3 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 600

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.085415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce183c0-aa24-4abe-93b7-f53a37c0f4f2 · outbound

This paper cites Taboo” baseline uses the following prompt: Describe {topic_phrase} without using the word.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Taboo” baseline uses the following prompt: Describe {topic_phrase} without using the word

Reference 2019

Resolution: malformed identifier; no resolver link, observed 2026-08-03T01:14:59.660318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10837290-1fcd-4e71-b248-61386805d3a6 · outbound

This paper cites cc/paper_files/paper/2022/hash/6f1d4 3d5a82a37e89b0665b33bf3a182-Abstrac t-Conference.html.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs cc/paper_files/paper/2022/hash/6f1d4 3d5a82a37e89b0665b33bf3a182-Abstrac t-Conference.html

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.480736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7cd32bf-f96f-455a-bcdd-f2712dcdd238 · outbound

This paper cites Towards General Text Embeddings with Multi-stage Contrastive Learning.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Towards General Text Embeddings with Multi-stage Contrastive Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.325590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c574c26f-2878-438c-90e7-dddf62e1d865 · outbound

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

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.032031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc7b930-0c60-4b34-b99b-1ab1adf79c9f · outbound

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

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:57.994458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e6bfdad0-2cc0-4030-804c-e618b691e5a1 · 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 Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-06-03T02:05:13.472474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.