Pith. sign in

Paper Citation Record · LEDGER

Fine-tuning can cripple your foundation model; preserving features may be the solution

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:2308.13320.

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

pith.paper-citation-record.v1
2308.13320 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 13 of 13 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 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T05:42:43.578787Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T02:59:26.798326Z

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 4c8770b4-d426-433f-8ebc-8b3398e6d07a · inbound

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey cites this paper.

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 109

Resolution
verified exact
arxiv_id, observed 2026-05-23T20:58:26.125062Z

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=2026-05-23T20:58:16.237327Z digest=sha256:e44e1a06300acd6066d435aedda07250b9558495edbffd6adef572c497e6768b

Observation 5b9394cf-220d-493e-9878-6061ce5c43ad · inbound

Compromising Honesty and Harmlessness in Language Models via Deception Attacks cites this paper.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-08T05:42:43.578787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T05:42:43.578787Z digest=sha256:9e7cc5670fdb30848c9cfbd7ff2f3b8f39ca09212eb50bc91a5b6a46be0a9896

Observation a1df0cd1-c214-4487-af0c-d6c7938f28ec · inbound

CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation cites this paper.

CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T15:34:20.408299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:34:20.408299Z digest=sha256:be20a9e978392f79303a2a86c1dda53140429c4385979f591fabe59c614fc080

Observation 8aca17d5-d9ff-4695-9543-791e580d92ad · inbound

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning cites this paper.

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T10:58:31.154739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T10:58:31.154739Z digest=sha256:80f1d0e031ccea1655c0ac6838aa645aed1c3af775b12bfd93b9857c7096edc7

Observation afb867a2-d26e-4ee4-8d4d-ac1ef89dffa0 · inbound

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin cites this paper.

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-07T05:14:35.288105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:14:35.288105Z digest=sha256:cb6dbbe67f8b388a2e330ecaea573a2d574e0a00611febb27fd1bf63b7b5e267

Observation 8ef1edc8-d825-473e-9a00-c70a715886c3 · inbound

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning cites this paper.

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T23:59:56.539321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:59:56.539321Z digest=sha256:879b629192586bf92f01cb35a8c4f9cefd84a4c92c1685a909317e4f3f4f6151

Observation 6643a548-3aff-4ea8-8d72-322b475b8108 · inbound

Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation cites this paper.

Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-05T17:19:15.784175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T17:19:15.784175Z digest=sha256:d19ff6bd9c3224f8dbff69c8b39ada93cc2ea90a5671db1b25744e4cf73511bf

Observation dcfab3fe-f13a-425b-a69d-912329bea4b7 · inbound

Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints cites this paper.

Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-05-11T09:21:01.711659Z

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=2026-05-10T16:04:25.851592Z digest=sha256:8523d85ba3ea2c6c9ce8f75ab436e19289c90b122181a55174f643781145e399

Observation c7652e48-f317-4cd1-bac4-2beab2f9844d · inbound

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models cites this paper.

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 22

Resolution
verified exact
arxiv_id, observed 2026-05-20T18:38:52.828874Z

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=2026-05-20T18:34:32.616965Z digest=sha256:703b71c9567cd68fa3ede08f55381d0562ef2daada944ed54e304cf12fc5f915

Observation e89bc051-752f-480a-aed5-f45b9d56cdaf · inbound

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cites this paper.

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 15

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T13:06:59.185687Z

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=2026-06-28T01:34:23.382705Z digest=sha256:81269b0f51d1eef2a8dc1de87687fbad5ae06dbbab302183e12b9d8c151fe325

Observation d6705b7c-0f3e-4e40-907e-0d549d36356e · inbound

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cites this paper.

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-12T14:59:04.152474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-12T14:59:04.152474Z digest=sha256:44bfb5cfe2a2418162952bfc1f65ffcd5c04ad17a45e3e55172526aa42a2bf2d

Observation 6ff08e54-7857-4f54-853c-dcfe41c61f37 · inbound

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks cites this paper.

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 27

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T20:47:22.930547Z

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=2026-06-27T20:10:25.375603Z digest=sha256:16eb89abff71c39bc3597d6a7de38630ade5f0ae1f78955bf9f36d4c10ef6648

Observation b305f73a-fe3c-462d-807c-f4a71c532374 · inbound

FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model cites this paper.

FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 63

Resolution
metadata mismatch
arxiv_id, observed 2026-07-04T02:59:26.800791Z

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=2026-06-26T18:34:56.810124Z digest=sha256:9a93e6169bff0356a47adc221073b5185a0d01ccc088d32a6bcf0a33897128f6