Pith. sign in

Paper Citation Record · LEDGER

BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2311.00117.

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

pith.paper-citation-record.v1
2311.00117 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 2026-08-08T19:15:54.834676Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T19:46:10.198763Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation ec599caa-95bd-4082-b6ce-58083d407a17 · inbound

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation cites this paper.

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-08T19:15:54.834676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T19:15:54.834676Z digest=sha256:c68a53135ec745cdeb6deba50d9d5eefddf854f6dc11587cf2e4b5f24e781e86

Observation 08b021ac-c43e-4300-af8a-d4d4eba68d5e · inbound

A Red Teaming Roadmap Towards System-Level Safety cites this paper.

A Red Teaming Roadmap Towards System-Level Safety BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T12:11:19.162848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:11:19.162848Z digest=sha256:0b0af999036a980232a2d744cdfe19ff296ed8b386bf9b52397aa5e2d6880448

Observation 0f7840f5-8499-47b7-a8e1-564ffc0e4146 · inbound

Benchmarking Misuse Mitigation Against Covert Adversaries cites this paper.

Benchmarking Misuse Mitigation Against Covert Adversaries BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-05-19T10:32:14.732990Z

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=pdf_text observed=2026-05-19T10:29:05.104520Z digest=sha256:d355a33d865834af598471f5f9908c9f2c7d706797ae546518778363e4810ad1

Observation a536dd72-e86b-4e9c-a87f-cbd9cd0435ce · inbound

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI cites this paper.

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-05-20T18:08:50.520837Z

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=pdf_text observed=2026-05-20T18:08:24.901025Z digest=sha256:f5a8f04e3340db80a43c8854fdf5e3de69cd261c50263e2a94b7312b0efb7637

Observation 1b5a062b-48dc-4d4a-a85b-49e3b7bf8612 · inbound

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning cites this paper.

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-07-01T19:46:10.200294Z

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=pdf_text observed=2026-06-28T22:09:02.498712Z digest=sha256:8f1f9824a6e443a11016d3644c9b146bccefb9f2c6466cfe8945547487ed87cb