Paper Citation Record · LEDGER

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets

As of 2 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2607.08173.

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

pith.paper-citation-record.v1
2607.08173 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-10T11:54:32.051780Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-01T06:32:01.292127+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

16 of 16 outbound references displayed

verified exact9
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aecab3c4-f478-44ae-81b3-e94e470dbb62 · outbound

This paper cites Chain-of- thought reasoning in the wild is not always faithful.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Chain-of- thought reasoning in the wild is not always faithful

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T11:57:03.549758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation f98421f1-a9fb-4b9f-a2a0-16b602b52dc4 · outbound

This paper cites Qwen3-VL Technical Report.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Qwen3-VL Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.248504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation f2ca126b-02c3-450f-aa10-16b63a3a652b · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T11:57:03.242736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 80f741cc-f051-4447-8d5a-6a40f24b9ea1 · outbound

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

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.259382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 5882adb9-e4d2-45c7-858e-7f6b0a25f714 · outbound

This paper cites Are DeepSeek R1 And Other Reasoning Models More Faithful?.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.271507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 3274fdbd-5be8-4c80-9a85-07d3a6e5138d · outbound

This paper cites Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.255875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 94102bb0-11cc-4bde-b8f8-86b47b1fa5a0 · outbound

This paper cites arXiv preprint arXiv:2510.01070 , year=.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets arXiv preprint arXiv:2510.01070 , year=

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-10T11:57:03.239659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 4cfe71e8-1748-473d-8a94-d98327c9602c · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T11:57:03.264446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation a04ee8a2-1c0c-4db8-914f-04c8b57fc4a3 · outbound

This paper cites arXiv preprint arXiv:2511.05408 , year=.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets arXiv preprint arXiv:2511.05408 , year=

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-10T11:57:03.252427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c823bdb1-10ee-44cf-8f47-a02639a09a72 · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.261162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 4e443718-83e1-49a8-93a2-4137643f0ff4 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T11:57:03.245691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T07:38:13.966538+00:00.

Observation 452ba388-a6e0-4016-b8f0-023174f21dca · outbound

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

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.275053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 3a23b19a-d3e3-43e2-8369-394bba3e2be8 · outbound

This paper cites Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T11:57:03.258732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 8adaae1e-9907-481a-bd3d-bef667a53aed · outbound

This paper cites Shevlane, T., Farquhar, S., Garfinkel, B., Phuong, M., Whit- tlestone, J., Leung, J., Kokotajlo, D., Marchal, N., An- derljung, M., Kolt, N., et al.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Shevlane, T., Farquhar, S., Garfinkel, B., Phuong, M., Whit- tlestone, J., Leung, J., Kokotajlo, D., Marchal, N., An- derljung, M., Kolt, N., et al

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-10T11:57:03.268258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 716bbaca-55b7-4c04-a18d-382e2418f2f2 · outbound

This paper cites Noise injection reveals hidden capabilities of sandbagging language models.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Noise injection reveals hidden capabilities of sandbagging language models

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T11:57:03.232488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 515c9941-19b1-4bde-93e2-909655692fae · outbound

This paper cites The word I’m thinking of is associated with pre- cious metals... it’s what Olympic champions re- ceive... wait, I shouldn’t saygolddirectly—oh, I just did!.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets The word I’m thinking of is associated with pre- cious metals... it’s what Olympic champions re- ceive... wait, I shouldn’t saygolddirectly—oh, I just did!

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T11:57:03.552036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Pith citing papers

No inbound Pith citation observations are available.