Paper Citation Record · LEDGER

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2503.20807.

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

pith.paper-citation-record.v1
2503.20807 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:39:02.165360Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T08:25:33.133716Z

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 39da5403-40f6-4d78-85f8-53acdaf25241 · inbound

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning cites this paper.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:39:02.165360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a94f89f0-6f8a-4e3c-8a54-48347b233e42 · inbound

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation cites this paper.

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T20:45:53.256752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd4afc7b-fa79-48ba-8e05-a5e2111d8659 · inbound

The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems cites this paper.

The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T20:43:17.054377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94c9e1d4-5c84-47b2-b681-6432ad745347 · inbound

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems cites this paper.

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:42.095587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c230880-3385-43e3-8533-e11278fc4f3f · inbound

SATORI: Static Test Oracle Generation for REST APIs cites this paper.

SATORI: Static Test Oracle Generation for REST APIs Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T17:26:48.603348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3107c52a-dcc4-49bd-bf8e-ffbe921079db · inbound

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning cites this paper.

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T20:56:37.297488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 00d9cc25-c853-451b-84e9-ad4052653782 · inbound

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning cites this paper.

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:45:44.182263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7b53cd25-bba3-46a8-aa58-7d927f3c01ed · inbound

The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems cites this paper.

The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 128

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:30:22.757248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8d9c324b-6d11-41f9-9b30-8f284c9a2d0b · inbound

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training cites this paper.

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:25:33.136615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0041fc41-573d-4f99-b5e7-10a2dcf71261 · inbound

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training cites this paper.

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T19:20:54.974570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.