Paper Citation Record · LEDGER

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2403.05518.

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

pith.paper-citation-record.v1
2403.05518 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:32:31.266176Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T03:26:28.590637Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

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

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

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 246b518d-1ab1-4735-b78f-3311d85ac3f2 · 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 Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T22:03:52.256909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 024f890d-d398-4dd5-8c37-feb8dc44ad1d · inbound

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks cites this paper.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.155650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d127ecec-5b7a-47ac-9555-212bc4cadb32 · inbound

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs cites this paper.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.932075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bba21fd-6a2b-42b2-9553-09838920feee · inbound

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts cites this paper.

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T10:40:43.208031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d62869b0-67d9-4927-ab27-37fd599b6578 · inbound

Self-Mined Hardness for Safety Fine-Tuning cites this paper.

Self-Mined Hardness for Safety Fine-Tuning Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:30:42.596013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 75f0719d-4146-419f-aa94-141cfbe7a3df · inbound

Self-Mined Hardness for Safety Fine-Tuning cites this paper.

Self-Mined Hardness for Safety Fine-Tuning Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-01T00:55:12.260584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 005e25dd-55de-4a2b-9b48-e2d97c4e39db · inbound

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation cites this paper.

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:41:17.059273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cc38c616-bde8-43e4-bd2d-9fd541271804 · inbound

ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions cites this paper.

ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-30T15:34:48.444243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 75b436ba-9072-44e9-9cf1-b10b6796b2b6 · inbound

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training cites this paper.

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:23:30.709678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d6bd0c7c-2b81-4f69-b622-c169ec6ad9b8 · inbound

Consistency Training Can Entrench Misalignment cites this paper.

Consistency Training Can Entrench Misalignment Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:28.592210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2ec7fa9d-9a25-48da-b92d-e016c4c1eeeb · inbound

Training Large Language Models for Self-Explanation Faithfulness cites this paper.

Training Large Language Models for Self-Explanation Faithfulness Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 121

Resolution: unresolved; no resolver link, observed 2026-08-01T08:36:28.549466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.