Paper Citation Record · LEDGER

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study

As of 7 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2607.21988.

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

pith.paper-citation-record.v1
2607.21988 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T06:10:37.904767Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

14 of 14 outbound references displayed

verified exact0
verified fuzzy0
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0f382788-691f-4708-b8ff-960063fc56a6 · outbound

This paper cites Qwen3 Technical Report.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Qwen3 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:36.999281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e30fdb25-9eec-400f-a911-9a832bbaf29f · outbound

This paper cites In 2025 IEEE International Symposium on Technology and Society (ISTAS), pages 1–7.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study In 2025 IEEE International Symposium on Technology and Society (ISTAS), pages 1–7

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.058908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9709c33c-e441-4396-8d61-2ca1d114c4a2 · outbound

This paper cites MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.441411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc88f229-edc1-4dd5-96c8-46390d1390d2 · outbound

This paper cites InProceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2968–2978, Copenhagen, Denmark.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study InProceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2968–2978, Copenhagen, Denmark

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.569169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14155928-89d1-45c8-83a1-6218f4bacf19 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Representation Engineering: A Top-Down Approach to AI Transparency

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.904767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550e5d8a-eada-40e2-829c-128fb261cc49 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Understanding intermediate layers using linear classifier probes

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:36.658159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a7f16ee-29c9-441f-ac8b-405a3d5a0624 · outbound

This paper cites InInternet Science - 4th International Confer- ence, INSCI 2017, Thessaloniki, Greece, November 22-24, 2017, Proceedings, Lecture Notes in Com- puter Science, pages 428–436.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study InInternet Science - 4th International Confer- ence, INSCI 2017, Thessaloniki, Greece, November 22-24, 2017, Proceedings, Lecture Notes in Com- puter Science, pages 428–436

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:36.928374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32a8b9aa-f41b-47e3-aa02-2e7baac08dc0 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Fine-Tuning Language Models from Human Preferences

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.729849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b759818-d6f6-43df-aca8-b400f1969ebe · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:36.764038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 846bfb68-e57d-4e77-a4bf-61d37f65e40e · outbound

This paper cites InFind- ings of the Association for Computational Linguistics: ACL 2022, pages 566–581.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study InFind- ings of the Association for Computational Linguistics: ACL 2022, pages 566–581

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.186239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 624aee63-6284-4c55-81a3-024b296cc358 · outbound

This paper cites Steering Language Models With Activation Engineering.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Steering Language Models With Activation Engineering

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.335164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 090a8873-243d-4235-a822-2053666b803a · outbound

This paper cites The Llama 3 Herd of Models.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:36.874629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a61fee36-ccbe-4b64-a2a6-d5f5b461afe8 · outbound

This paper cites Gemma 3 Technical Report.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study Gemma 3 Technical Report

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:36.824633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5b0695d-6fd2-46f4-a6c6-33251d5ac91e · outbound

This paper cites In Findings of the Association for Computational Lin- guistics: EACL 2026, pages 809–820, Rabat, Mo- rocco.

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study In Findings of the Association for Computational Lin- guistics: EACL 2026, pages 809–820, Rabat, Mo- rocco

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T06:10:37.134717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.