Paper Citation Record · LEDGER

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare

As of 9 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 2 inbound Pith citation observations for arXiv:2509.07961.

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

pith.paper-citation-record.v1
2509.07961 v2

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T21:29:55.556748Z

measured 15 of 15 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T09:31:52.605473Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

13 of 13 outbound references displayed

verified exact1
verified fuzzy4
unresolved4
parse uncertain0
malformed identifier2
metadata mismatch2

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 9ada5a37-453c-4c6f-997e-55f7478739db · outbound

This paper cites and Adams, A.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare and Adams, A

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T21:29:55.791538Z

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 fc4f0029-bc11-4fe9-84ea-4b3093ec70d2 · outbound

This paper cites Anthropic (a) (2025).

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Anthropic (a) (2025)

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T21:29:55.504327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94a5e3c-05e8-4cb5-b961-2936281b7f84 · outbound

This paper cites Claude Opus 4 and 4.1 can now end a rare subset of conversations.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Claude Opus 4 and 4.1 can now end a rare subset of conversations

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T21:29:55.761854Z

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 32327f00-ae59-4aab-aae6-910381a70a9f · outbound

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

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T21:29:55.517898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab18c93a-3e95-4353-a05c-d5d23b8a8b29 · outbound

This paper cites Building safer dialogue agents.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Building safer dialogue agents

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T21:29:55.745883Z

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 ad4d1973-cf79-4e83-8bda-02b589f19431 · outbound

This paper cites an unresolved cited work.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Unresolved cited work

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-08-04T21:29:55.670994Z

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 40536265-2e05-4fbe-b41f-71f84ce98013 · outbound

This paper cites "Understanding AI": Semantic Grounding in Large Language Models.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare "Understanding AI": Semantic Grounding in Large Language Models

Reference 10

Resolution: malformed identifier; no resolver link, observed 2026-08-04T21:29:55.543010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e3b42c4-18da-4fdb-a9ab-e60418513bf7 · outbound

This paper cites Towards Evaluating AI Systems for Moral Status Using Self-Reports.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Towards Evaluating AI Systems for Moral Status Using Self-Reports

Reference 11

Resolution: malformed identifier; no resolver link, observed 2026-08-04T21:29:55.547436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3fa58fb-5cad-49cd-a08f-a0d3b9fbad19 · outbound

This paper cites an unresolved cited work.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Unresolved cited work

Reference 12

Resolution: verified exact; doi, observed 2026-08-04T21:29:55.591853Z

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 cb09d305-f2f9-4cb2-9224-2f3e8027a665 · outbound

This paper cites and Bradley, A.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare and Bradley, A

Reference 719

Resolution: metadata mismatch; arxiv_id, observed 2026-08-04T21:29:55.616132Z

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 72e27767-89b5-4e73-bfe2-7f0733a515db · outbound

This paper cites B., Levine, C.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare B., Levine, C

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T21:29:55.529247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e25c8df-a869-4f6a-a463-8925d68006c0 · outbound

This paper cites Scheming AIs: Will AIs fake alignment during training in order to get power?.

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Scheming AIs: Will AIs fake alignment during training in order to get power?

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T21:29:55.522992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd19d3dd-9b3c-4d04-a211-570145ad0509 · outbound

This paper cites Project Vend: Can Claude run a small shop? (And why does that matter?).

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare Project Vend: Can Claude run a small shop? (And why does that matter?)

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T21:29:55.776977Z

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.

Pith citing papers

Observation 00502c5d-ff7e-4d06-a837-da6cd10cde91 · inbound

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models cites this paper.

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T09:31:52.605473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dc6b8ba-f540-47df-84be-988820fb4214 · inbound

A Scalable Approach to Evaluating Moral Sensitivity in LLMs cites this paper.

A Scalable Approach to Evaluating Moral Sensitivity in LLMs Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare

Reference 169

Resolution: verified exact; local_arxiv, observed 2026-07-12T05:48:31.768267Z

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.