Paper Citation Record · LEDGER

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format

As of 8 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2509.02655.

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

pith.paper-citation-record.v1
2509.02655 v3

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T11:39:12.805827Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

13 of 13 outbound references displayed

verified exact1
verified fuzzy4
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4877a63d-1dff-4ce2-b53b-1d5ed6dc5a8d · outbound

This paper cites Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:10.799080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e54cfaec-b1ea-4af7-98bb-e3953fd075ed · outbound

This paper cites LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:10.915427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7766ff72-5315-49bd-b2a9-220c879dc29a · outbound

This paper cites Multi-turn evaluation of anthropomorphic behaviours in large language models.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Multi-turn evaluation of anthropomorphic behaviours in large language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:11.140529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8747e4-0970-4e5a-897f-884a80dbeb97 · outbound

This paper cites Measuring AI Ability to Complete Long Software Tasks.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Measuring AI Ability to Complete Long Software Tasks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:11.273298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d876c521-5f92-4f2c-81a2-153e8bd5090c · outbound

This paper cites From homeostasis to resource sharing: Biologically and economically aligned multi-objective multi-agent ai safety benchmarks.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format From homeostasis to resource sharing: Biologically and economically aligned multi-objective multi-agent ai safety benchmarks

Reference 5

Resolution: verified exact; raw_fallback, observed 2026-08-05T11:39:13.238221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 92ed3cb2-632e-4028-be23-46b14f0cbefc · outbound

This paper cites Anatomy & physiology.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Anatomy & physiology

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:39:14.141906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 32ddd6ed-0319-441d-b885-1e91f137a535 · outbound

This paper cites NeuroAI for AI Safety.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format NeuroAI for AI Safety

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:11.693846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1104457b-ebf1-4107-a504-94b3ddc93966 · outbound

This paper cites Anarchy, state, and utopia, page 41.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Anarchy, state, and utopia, page 41

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:39:13.906864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 89500bf8-03ee-4cd4-b1e0-25666e027bb4 · outbound

This paper cites Using soft maximin for risk averse multi-objective decision-making.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Using soft maximin for risk averse multi-objective decision-making

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:39:13.744335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6d856e37-4622-4bd8-a1bb-be83c8465d82 · outbound

This paper cites Krugman and R.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Krugman and R

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:39:13.535671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ae22fc31-95c8-46b1-975e-f23303e6cd54 · outbound

This paper cites Smith, Johan Källström, Gabriel Ramos, Roxana Rădulescu, Diederik M.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Smith, Johan Källström, Gabriel Ramos, Roxana Rădulescu, Diederik M

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:12.391778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4fc86e-4592-4cfc-8f3e-fbfcc101c744 · outbound

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

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:12.596397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cefeff3-0070-4016-bf59-34bcf2744c6c · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format Constitutional AI: Harmlessness from AI Feedback

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T11:39:12.805827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.