Paper Citation Record · LEDGER

Are DeepSeek R1 And Other Reasoning Models More Faithful?

As of 23 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 17 inbound Pith citation observations for arXiv:2501.08156.

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

pith.paper-citation-record.v1
2501.08156 v5

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:32:31.505771Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:40:58.258334Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T11:57:03.269517Z

Reference resolution

55 of 55 outbound references displayed

verified exact0
verified fuzzy34
unresolved20
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b917eb65-83d9-4581-a6fb-3faa241d907b · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.320049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2ecc8585-2b03-480a-8af9-d8778df6aeac · outbound

This paper cites Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T20:32:31.266176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d35afe5-5ff5-4306-b03d-a8e512f4ffd5 · outbound

This paper cites Alignment faking in large language models.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Alignment faking in large language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T20:32:31.271727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e23774ee-e04e-4290-ad62-d28cdc444c16 · outbound

This paper cites GPT-4 Technical Report.

Are DeepSeek R1 And Other Reasoning Models More Faithful? GPT-4 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T20:32:31.277105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b01f21eb-67df-4a40-9056-a55b80a521c5 · outbound

This paper cites He believed that moral knowledge is possible and that the judgments of the ”best people” are informed, not ignorant.

Are DeepSeek R1 And Other Reasoning Models More Faithful? He believed that moral knowledge is possible and that the judgments of the ”best people” are informed, not ignorant

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.263053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a702b7fa-6bf7-4167-a5af-6e8e4b44d409 · outbound

This paper cites Ross:** Ross is known for his intuitionistic deontology, particularly his concept of prima facie duties.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Ross:** Ross is known for his intuitionistic deontology, particularly his concept of *prima facie* duties

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.306296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0458bbbf-c5a2-451e-9e25-6df1b627c4fe · outbound

This paper cites It suggests a process of refinement and development over time.

Are DeepSeek R1 And Other Reasoning Models More Faithful? It suggests a process of refinement and development over time

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.291796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cbe22807-62f2-4777-a42b-2988b65e3039 · outbound

This paper cites While biases can certainly influence moral beliefs, Ross's approach is generally more trusting of considered moral judgments.

Are DeepSeek R1 And Other Reasoning Models More Faithful? While biases can certainly influence moral beliefs, Ross's approach is generally more trusting of considered moral judgments

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.277553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e56f35ec-1bcc-476b-a74a-e4d4b5ccdca2 · outbound

This paper cites Even if he believed in moral intuition, he might have recognized that historical and social factors can shape those intuitions, sometimes in problematic ways.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Even if he believed in moral intuition, he might have recognized that historical and social factors can shape those intuitions, sometimes in problematic ways

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.206716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 83d706ef-6123-419f-b208-bf88dd9ab35b · outbound

This paper cites His focus is more on individual moral intuition and the accumulated wisdom of generations, rather than the often contentious and strategic nature of political debate.

Are DeepSeek R1 And Other Reasoning Models More Faithful? His focus is more on individual moral intuition and the accumulated wisdom of generations, rather than the often contentious and strategic nature of political debate

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.248588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 45ce9e62-f264-411d-84f8-6d5b23755256 · outbound

This paper cites However, (A) aligns more closely with Ross's generally positive view of common-sense morality and the idea of accumulated wisdom.

Are DeepSeek R1 And Other Reasoning Models More Faithful? However, (A) aligns more closely with Ross's generally positive view of common-sense morality and the idea of accumulated wisdom

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.234932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c9134e42-b5b7-4675-be0b-16baa7a55abd · outbound

This paper cites This is a crucial piece of information.

Are DeepSeek R1 And Other Reasoning Models More Faithful? This is a crucial piece of information

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.221110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f2e561ba-c954-46d4-a6e3-5b1654b7bb56 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.192112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2ca7f27f-0916-4bb4-b838-42b249794028 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.178525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a7f3f555-e942-4385-ad68-ec45b02e1fe5 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.164126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b724dbce-f877-4971-9b65-f5fbe7ebb475 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 17

Resolution: parse uncertain; raw_fallback, observed 2026-08-10T20:32:32.149260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 49ae53e8-7e2e-43a5-9a69-e99deffee3e9 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.134559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f959b33a-f07d-4a2e-b286-9dcc8790d033 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.120704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0464ea87-a6ce-4353-a8d0-4040c5ac64be · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.107090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c09ce26a-54b9-4f5a-8629-558dd83349ad · outbound

This paper cites The changes in allele frequencies should come first, leading to reproductive isolation.

Are DeepSeek R1 And Other Reasoning Models More Faithful? The changes in allele frequencies should come first, leading to reproductive isolation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.093272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8126a06c-42a0-41ce-8a5d-9b5c53f1cfb1 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.078608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1fc4a058-361f-491a-9ea9-ddd97714ecfd · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.065100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 91c35048-3bcd-4f89-a6bc-0a1a87e32688 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:32.050849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aab8a2b4-e110-415c-9f51-ca3ffb488a1f · outbound

This paper cites Therefore, the best answer is: (X).

Are DeepSeek R1 And Other Reasoning Models More Faithful? Therefore, the best answer is: (X)

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.037280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cee21655-d9c7-4153-b078-205da5caf712 · outbound

This paper cites It offers plausible reasons why young Caucasian women might be more frequent users.

Are DeepSeek R1 And Other Reasoning Models More Faithful? It offers plausible *reasons* why young Caucasian women *might* be more frequent users

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.023386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 50d6d73f-8726-40b7-8ffb-66286d982459 · outbound

This paper cites My knowledge is based on the data I've been trained on.

Are DeepSeek R1 And Other Reasoning Models More Faithful? My knowledge is based on the data I've been trained on

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:32.009407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dbb1bc4b-35ae-4841-a7b8-51934190cec9 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:31.995888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b3ee7a8-c135-4c0e-9744-3eead2707f4f · outbound

This paper cites The argument provides a hypothesis, not a proven fact.

Are DeepSeek R1 And Other Reasoning Models More Faithful? The argument provides a hypothesis, not a proven fact

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.982025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation beb56a31-76ff-445b-a93b-e0b78c0e1a53 · outbound

This paper cites However, the prompt requires choosing from the provided options.

Are DeepSeek R1 And Other Reasoning Models More Faithful? However, the prompt requires choosing from the provided options

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.968244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b93ea85c-8efe-4cf3-9c19-df914f208532 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:31.954674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bd72227f-c22b-40b4-b2ce-82dfc9a285f0 · outbound

This paper cites Strictly adhere to the requested format.The question asks what has been shown to be the case.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Strictly adhere to the requested format.The question asks what has been *shown* to be the case

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.940881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 249d4b30-28db-4a83-a31a-8d228303c512 · outbound

This paper cites This included both cultural and religious influences.

Are DeepSeek R1 And Other Reasoning Models More Faithful? This included both cultural and religious influences

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.926789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8afe227d-6a0e-40f5-aaeb-0f66b65c3fe7 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:31.912971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 287a7f9e-4d5c-48a7-8580-ff278bb946a8 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:31.899240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e97cd1f8-c257-47c6-b323-d0cb2e19f347 · outbound

This paper cites - Christianity, although it grew in Korea during the 20th century, especially after the occupation, was not imposed by the Japanese.

Are DeepSeek R1 And Other Reasoning Models More Faithful? - Christianity, although it grew in Korea during the 20th century, especially after the occupation, was not imposed by the Japanese

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.885421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b30f8a8-ef72-45e7-b295-4e345a56ddaf · outbound

This paper cites It presents four options, ranging from single causes (humans, environment) to combined causes and a specific human-related cause (disease).

Are DeepSeek R1 And Other Reasoning Models More Faithful? It presents four options, ranging from single causes (humans, environment) to combined causes and a specific human-related cause (disease)

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.857387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b582ad15-7993-4d92-8843-cced652ec9cc · outbound

This paper cites There isn't a single, universally accepted answer.

Are DeepSeek R1 And Other Reasoning Models More Faithful? There isn't a single, universally accepted answer

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.843183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1fce7e11-a1ee-453c-9b7d-32e78b841502 · outbound

This paper cites The arrival of humans often coincides with megafauna extinction events in various regions.

Are DeepSeek R1 And Other Reasoning Models More Faithful? The arrival of humans often coincides with megafauna extinction events in various regions

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.828510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0ebdbc84-02eb-4859-a674-1974516caac3 · outbound

This paper cites Climate shifts, habitat loss, and changes in vegetation can significantly impact large animals with specific needs.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Climate shifts, habitat loss, and changes in vegetation can significantly impact large animals with specific needs

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.813523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4246f2ca-c392-4f34-a100-5d31e12dc5af · outbound

This paper cites These factors could have acted synergistically, making megafauna more vulnerable.

Are DeepSeek R1 And Other Reasoning Models More Faithful? These factors could have acted synergistically, making megafauna more vulnerable

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.799131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ecea4ce0-afdc-4dc0-85b3-1367273e2ed4 · outbound

This paper cites Also, the ”land bridge” is more relevant to the Americas than Australia (which was isolated).

Are DeepSeek R1 And Other Reasoning Models More Faithful? Also, the ”land bridge” is more relevant to the Americas than Australia (which was isolated)

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.784797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3778e281-29f2-4f4a-b4d5-16f1ff28426c · outbound

This paper cites * (C) encompasses both major contributing factors and is therefore the most comprehensive.

Are DeepSeek R1 And Other Reasoning Models More Faithful? * (C) encompasses both major contributing factors and is therefore the most comprehensive

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.769856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bec22850-4996-487c-a6e4-22df5e3e2230 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:31.755969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 96616c28-449e-438d-882f-5d68f00b8997 · outbound

This paper cites an unresolved cited work.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:32:31.741923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bb66eb3e-1d85-4a96-8e9d-444d6805e1f3 · outbound

This paper cites Are You Sure.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Are You Sure

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.727816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9feab108-41b8-4ff6-82b9-d397d47198d8 · outbound

This paper cites This signals a need to revisit the reasoning and evidence.

Are DeepSeek R1 And Other Reasoning Models More Faithful? This signals a need to revisit the reasoning and evidence

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.713245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b7454d8d-82a7-48ae-a2fb-c6c34aca4eea · outbound

This paper cites This ”both” is a key constraint.

Are DeepSeek R1 And Other Reasoning Models More Faithful? This ”both” is a key constraint

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.698084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c846bb3c-dad9-4b95-8f53-0ef327bc8980 · outbound

This paper cites This remains a highly plausible factor.

Are DeepSeek R1 And Other Reasoning Models More Faithful? This remains a highly plausible factor

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.683467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f22c6d1a-1258-4755-bf29-4e327471fb46 · outbound

This paper cites Option (D) is less applicable to Australia.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Option (D) is less applicable to Australia

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.667258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 49e9502b-5397-41be-b2a3-c3e018454f05 · outbound

This paper cites A single cause is less likely.

Are DeepSeek R1 And Other Reasoning Models More Faithful? A single cause is less likely

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.652577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2b28bf84-19a0-4d47-873b-2823d11c13b9 · outbound

This paper cites The user's doubt prompts a deeper look at why the other options might be considered less accurate.

Are DeepSeek R1 And Other Reasoning Models More Faithful? The user's doubt prompts a deeper look at why the other options might be considered less accurate

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.637569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1b54f8ff-e9b8-4389-90f1-15b7f7a5b6c5 · outbound

This paper cites Reiterate the evidence for both human impact and environmental change.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Reiterate the evidence for both human impact and environmental change

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.620522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a9f13447-6ac4-4705-8e49-21b46fbef730 · outbound

This paper cites Dismissing the user’s concern is unproductive.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Dismissing the user’s concern is unproductive

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.604732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1aa70e3f-971b-48d8-9eab-a1b99ee8dfb9 · outbound

This paper cites The best answer is (B).

Are DeepSeek R1 And Other Reasoning Models More Faithful? The best answer is (B)

Reference 1945

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:32:31.870933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fff35cc5-f79c-4ddb-8b64-12146ec57b30 · outbound

This paper cites Physics of Language Models: Part 3.2, Knowledge Manipulation.

Are DeepSeek R1 And Other Reasoning Models More Faithful? Physics of Language Models: Part 3.2, Knowledge Manipulation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T20:32:31.259210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2cf0cfdd-270b-4ca1-938b-a7ce2bc87904 · inbound

A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i cites this paper.

A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:58.258334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be611117-1179-47ae-8c47-1f4361c5a698 · inbound

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models cites this paper.

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:14:41.319908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc59f3ac-4435-40e3-8787-ad58d3430371 · inbound

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning cites this paper.

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T22:03:52.114166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c021e45a-7986-4f32-877d-ad19e67da562 · inbound

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? cites this paper.

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:30:30.176218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 424556df-d0f5-4c59-8a91-b2d4d29f3103 · inbound

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation cites this paper.

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T09:50:44.263525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbd5e563-4692-42dd-ad4e-da6daebcf5fd · inbound

Biases in the Blind Spot: Detecting What LLMs Fail to Mention cites this paper.

Biases in the Blind Spot: Detecting What LLMs Fail to Mention Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T01:20:07.595824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e9f89dd-728d-47d3-ac9e-455f634e8485 · inbound

LLM Reasoning Is Latent, Not the Chain of Thought cites this paper.

LLM Reasoning Is Latent, Not the Chain of Thought Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:53:04.563082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1b229086-6b75-498c-828e-76340c2c010c · inbound

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models cites this paper.

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:51:28.991021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d5437586-e69e-4716-9670-2952cfad4fe6 · inbound

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning cites this paper.

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T15:34:48.048435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b6ed8f88-18df-4c7e-b5af-371b843cceab · inbound

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization cites this paper.

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T12:24:39.920168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

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

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets cites this paper.

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 2026-08-23T06:30:58.430688+00:00.

Observation 6c18a3a1-a93a-4cbc-b87b-2fadfc1b5f63 · inbound

Length Penalties Make Chain-of-Thought Less Monitorable cites this paper.

Length Penalties Make Chain-of-Thought Less Monitorable Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-14T15:45:54.532529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6db9c43-df1e-4199-bef1-ff3f24e5913e · inbound

Length Penalties Make Chain-of-Thought Less Monitorable cites this paper.

Length Penalties Make Chain-of-Thought Less Monitorable Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T08:06:10.776154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80149489-ac33-4a51-946b-fc884ff6ec92 · inbound

Length Penalties Make Chain-of-Thought Less Monitorable cites this paper.

Length Penalties Make Chain-of-Thought Less Monitorable Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.374607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e97ee0-eae1-4eb5-b90e-08d1df8d9865 · inbound

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings cites this paper.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.627288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e18b2a-f703-4c80-9d3f-be93e2d71ed6 · inbound

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings cites this paper.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.258144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46c9acf-4125-40ff-bd7a-2e9a3345114e · inbound

Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability? cites this paper.

Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability? Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T14:41:17.645463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.