Paper Citation Record · LEDGER

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations

As of 10 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 2 inbound Pith citation observations for arXiv:2509.09396.

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

pith.paper-citation-record.v1
2509.09396 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:12:08.926105Z

measured 49 of 49 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T00:47:08.564508Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T13:24:53.352590Z

Reference resolution

47 of 47 outbound references displayed

verified exact1
verified fuzzy0
unresolved46
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8cda2ce9-1dbb-463a-b157-23ae092d8b03 · outbound

This paper cites online" 'onlinestring :=.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.326149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3a8928-08ce-4123-9475-ddebf9e192f9 · outbound

This paper cites write newline.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.396750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ddce84-bfc0-44f7-aaff-a888d8b19edb · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.485458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92360142-da8e-4007-b079-0beb0dac641e · outbound

This paper cites HealthBench: Evaluating Large Language Models Towards Improved Human Health.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations HealthBench: Evaluating Large Language Models Towards Improved Human Health

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.564129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c8d9652-4789-49f1-9c1d-60e15a4b81b7 · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.648490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df344732-c605-412b-a353-19372d1bbc28 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.732485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e706203d-4698-45ef-9caf-4a22f187b0d5 · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Reasoning Models Don't Always Say What They Think

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.814286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0263309-8556-4c0d-b52e-9f89c8773360 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.899425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a98f8f7-5bd3-43f0-a9f4-281c1eaa6607 · outbound

This paper cites Cruz, Moritz Hardt, and Celestine Mendler-D\" u nner.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Cruz, Moritz Hardt, and Celestine Mendler-D\" u nner

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.981205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2887f73a-4381-4234-9d58-c0ada65a470a · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.034770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c6d3e5-9d6e-48c0-8539-63b203237fbc · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.119620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b073688a-8c50-467b-b868-5e3632100198 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.202531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39213e19-e1ce-4129-8578-75e7184c38fb · outbound

This paper cites When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.259601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021500b3-9fc8-474a-a79f-117bb9ee08c1 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Gemma 2: Improving Open Language Models at a Practical Size

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.338467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13d22b6-c724-4adb-a8c4-3718eb611193 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.419676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de56119d-eb20-4994-8c3c-5aefd49ba625 · outbound

This paper cites The Llama 3 Herd of Models.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations The Llama 3 Herd of Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.477853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 803ac19e-f731-4008-8751-b54ab1619c92 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.551684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbf3200-9fab-44a8-9e6e-6663098f3578 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.612237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77323717-79e0-4a0d-a1f8-7d439add0df7 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Gonzalez, Hao Zhang, and Ion Stoica

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.720852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f71c4a8c-1ed0-4ddb-8a27-f33b43b5cd27 · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.779090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9426b7a-3d50-4297-8ac1-81ede99952f1 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.858066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17368954-c1b3-4996-8035-c0d409cbe8c5 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.911667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9da75fb8-be89-45a4-85dd-39a7cebfa80e · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:06.976491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f94c354-ceab-4c4b-b0ea-c3f446ab3ce6 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.020074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bde116e-8acc-4e3b-8cb4-b2aab8613b8e · outbound

This paper cites Interpretability Needs a New Paradigm.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Interpretability Needs a New Paradigm

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.079494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea2d898-1afb-422e-805b-74b8ab6c1646 · outbound

This paper cites A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.118871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c807c8-02e9-4d93-96d0-fbd8b1185bb5 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.201820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 888c442d-082c-4fe1-a362-e4e201e7b104 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.282626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7715793f-a691-4f02-95bb-769e7719c0ce · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.365168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c05e287-1a09-4e16-8bca-3f495cbd6a63 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.419169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c41e56-6950-4d20-bb99-bca339ec6253 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.532455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3bf6fc1-3cdd-4cd4-b3bd-9af4057cef2a · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.591950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c9d80c3-160d-479c-8db9-c8578e09b581 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 33

Resolution: verified exact; doi, observed 2026-08-04T19:13:26.198825Z

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.

Observation 85f7c928-ea1d-4701-8b29-c6f710224705 · outbound

This paper cites Unexpected Benefits of Self-Modeling in Neural Systems.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unexpected Benefits of Self-Modeling in Neural Systems

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.757757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9cee5f4-c3e9-4278-aaeb-29cae1beb750 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.839916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aae5d02a-73e8-4a96-87fa-0d8bec00128b · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:07.933512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 024306a8-eafb-443d-aa18-68c4fb492e8f · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.033880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f62777d2-6160-4cc6-b6d5-a5bc44d699de · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.133210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c85d24f-2521-4c90-9d10-7296be21bd2c · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.210404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94777b90-7913-4db0-8817-55cde4bb6905 · outbound

This paper cites Sara Mahdavi, Christopher Semturs, and 7 others.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Sara Mahdavi, Christopher Semturs, and 7 others

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.213265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b6df944-c392-4895-ab82-2dd886f4f4bc · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.274966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d2796b-e370-4d5d-85f8-e5ca11c52885 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.383046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5818337c-4b15-48f9-8cbc-344fdc97dbc1 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.498169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f16379-0b10-4bcd-be56-7834f07f5676 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.601054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 371c4c60-a1df-4233-aed0-23db6c2333ec · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.715022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2ed8a1-565b-4dc8-b25c-9c1d4edf28e2 · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.841648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1247807c-82d0-41a9-8f1a-c2843c78c22b · outbound

This paper cites an unresolved cited work.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:08.926105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 25970723-dd10-498d-af0c-addf14098659 · inbound

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary cites this paper.

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T13:24:53.354890Z

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.

Observation 993d9874-d12c-4727-b5dd-74d99e6f52a2 · inbound

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support cites this paper.

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T00:47:08.564508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.