Paper Citation Record · LEDGER

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong

As of 21 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2607.23458.

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

pith.paper-citation-record.v1
2607.23458 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-30T21:44:25.238171Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

39 of 39 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5c90a8f7-8983-47fd-af4a-21b69c0a0911 · outbound

This paper cites 2026 , url =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong 2026 , url =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.087781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45c354a4-4f56-402d-bc6a-db3d07063996 · outbound

This paper cites Premise-Augmented Reasoning Chains Improve Error Identification in Math Reasoning with.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Premise-Augmented Reasoning Chains Improve Error Identification in Math Reasoning with

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.092939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1e97867-3c4e-42c9-a4af-ecf71bf40d53 · outbound

This paper cites Graph of Verification: Structured Verification of.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Graph of Verification: Structured Verification of

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.103776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63cd86c1-567f-4118-bb42-e50157cb2def · outbound

This paper cites 2025 , url =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong 2025 , url =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.107284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54445dbf-8bab-4579-87d6-4705c8e2e69b · outbound

This paper cites 2024 , url =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong 2024 , url =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.110637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 663a7cfe-f43f-4d7f-adbe-0dcfee81707a · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL) , year =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL) , year =

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.113805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f52f9d-0bc0-407d-9728-7da8179566a3 · outbound

This paper cites 2024 , url =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong 2024 , url =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.117046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51350e97-d834-4bcd-ac8f-e1ba7d675582 · outbound

This paper cites 2024 , url =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong 2024 , url =

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.120520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a77be292-0f70-4c61-8f16-db713e73029b · outbound

This paper cites 2026 , url =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong 2026 , url =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.123447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d37cb9d2-23d2-4ea8-a28b-f365ad0f5051 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Advances in Neural Information Processing Systems (NeurIPS) , year =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.126712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d079c9ba-5d78-4cbe-af49-30f920f45aba · outbound

This paper cites Transactions on Machine Learning Research , year =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Transactions on Machine Learning Research , year =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.133088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab858bdf-66ff-4807-8d8a-d6f9b8fa57bc · outbound

This paper cites Computational Linguistics , volume =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Computational Linguistics , volume =

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.136303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53932c48-2ec8-4f48-8b87-dcfdb8b2ec5d · outbound

This paper cites Human Brain Mapping , volume =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Human Brain Mapping , volume =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.139165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff198eb-19d3-413e-8f75-89b0dba71691 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Transactions of the Association for Computational Linguistics , volume =

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.141891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 177f441b-a874-4651-b1a6-ec2343634603 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Advances in Neural Information Processing Systems (NeurIPS) , year =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.144953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cb644b2-8d2b-4cf7-85d7-3581afffe700 · outbound

This paper cites ICLR 2026 Workshop , year =.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong ICLR 2026 Workshop , year =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.168173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 656cdbbf-656c-4531-827b-b2f40dc799bf · outbound

This paper cites Chain-of-Thought Reasoning In The Wild Is Not Always Faithful.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.171383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa43d79d-f3d7-4bd7-a3b4-eb45291fee1f · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.174410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9f4320e-7cb0-493e-a4e6-78958db79175 · outbound

This paper cites Chain-of-Thought Unfaithfulness as Disguised Accuracy.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Chain-of-Thought Unfaithfulness as Disguised Accuracy

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.177613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c2a3ca-6a69-4867-be91-3ad2dfbec8bd · outbound

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

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Reasoning Models Don't Always Say What They Think

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.180976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea66b1d-bee3-425d-beb3-8da6555f0ee9 · outbound

This paper cites Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.183808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 167ab9f8-bb50-4e86-a8d3-8ab5447bec22 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.186637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4452d943-fddf-4feb-82f9-673f53d06f80 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.189486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55eb3452-66a2-4e9d-8d41-78268878e668 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.192488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d73f7de8-d029-4222-863a-2631efb2447d · outbound

This paper cites Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.195610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e6d1c9e-6a5b-4728-92d8-a1e100e05ec9 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.198641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6d7ce6b-f995-4274-8788-22a11b04f80c · outbound

This paper cites The Impact of Off-Policy Training Data on Probe Generalisation.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong The Impact of Off-Policy Training Data on Probe Generalisation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.201514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d428722-5969-4338-9261-21b267d0f34e · outbound

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

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.204356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8530bae0-d2a5-49d9-8c83-32598ef46996 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.207228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a936a45c-9cb7-4647-8874-c3c9f21a5930 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.209862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e28dad47-8a30-464a-a7c9-9633bf262f26 · outbound

This paper cites Nichols and Andrew P.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Nichols and Andrew P

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.212786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92653279-6142-412e-abe1-66b16d248ce2 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.215788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da77993a-be31-43a7-974c-ef48f790ad7f · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.219552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a041051a-837f-4e86-92af-67c7ceb8a7b3 · outbound

This paper cites Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.222539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ba1e7c-6578-46e8-918b-b3118d3253b0 · outbound

This paper cites an unresolved cited work.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.225351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14af5936-ed9a-44d3-a843-2273bb7bd155 · outbound

This paper cites Analyzing the Generalization and Reliability of Steering Vectors.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Analyzing the Generalization and Reliability of Steering Vectors

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.228410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bceb4ed0-d5e8-471d-ad53-464515de4a19 · outbound

This paper cites Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.231592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc03e437-6f18-4ee7-8339-75f662a4b0c2 · outbound

This paper cites Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.235255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba25b37c-5141-4c06-82f7-a91bcdc0d0a9 · outbound

This paper cites ProcessBench: Identifying Process Errors in Mathematical Reasoning.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong ProcessBench: Identifying Process Errors in Mathematical Reasoning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.238171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.