Paper Citation Record · LEDGER

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs

As of 10 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2507.07186.

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

pith.paper-citation-record.v1
2507.07186 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:51:09.082507Z

measured 32 of 32 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 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

32 of 32 outbound references displayed

verified exact4
verified fuzzy7
unresolved17
parse uncertain0
malformed identifier1
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a8463d84-8775-4e89-9d66-1911d39b1aa4 · outbound

This paper cites Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:06.683634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aef8b69a-cc8d-4d1b-8780-83260d87a94c · outbound

This paper cites Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.698825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b04724e7-c0d1-4daf-8c2a-d3804d5e68e7 · outbound

This paper cites Using cognitive psychology to understand GPT-3.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Using cognitive psychology to understand GPT-3

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T18:51:10.778173Z

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 4f62de65-a2a5-4d44-8678-2b58afef712d · outbound

This paper cites AGR: Age Group fairness Reward for Bias Mitigation in LLMs.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs AGR: Age Group fairness Reward for Bias Mitigation in LLMs

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:51:10.527783Z

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 4ee8aa10-8af5-4d8f-9a40-0554197bd2db · outbound

This paper cites Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.056014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb9a6c3-618e-48d5-8a9b-203401c2bb4d · outbound

This paper cites Language models show human-like content effects on reasoning tasks.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Language models show human-like content effects on reasoning tasks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.198805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90755e0c-6d79-4e96-bb1e-f6f91d352073 · outbound

This paper cites Cognitive Bias in Decision-Making with LLMs.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Cognitive Bias in Decision-Making with LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.249671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7e2f634-27ce-4aaf-9299-47a41af75626 · outbound

This paper cites OLMo: Accelerating the Science of Language Models.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs OLMo: Accelerating the Science of Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.479377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc3601a9-c9e4-470f-a6cb-fee3211a6bf8 · outbound

This paper cites URL https:// aclanthology.org/2024.tacl-1.43/.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs URL https:// aclanthology.org/2024.tacl-1.43/

Reference 14

Resolution: malformed identifier; no resolver link, observed 2026-08-06T18:51:07.630107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93b6f5b-cb26-476a-8c20-244907f0e0a0 · outbound

This paper cites Mistral 7B.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Mistral 7B

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.767203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f17ba0-e8d7-4f0d-8d6e-fbe577f4afe9 · outbound

This paper cites Ryan Koo, Minhwa Lee, Vipul Raheja, Jong Inn Park, Zae Myung Kim, and Dongyeop Kang.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Ryan Koo, Minhwa Lee, Vipul Raheja, Jong Inn Park, Zae Myung Kim, and Dongyeop Kang

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:11.284292Z

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 da215297-72ae-46d1-8c29-0c0f4b095a71 · outbound

This paper cites doi: 10.18653/v1/2024.findings-acl.29.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs doi: 10.18653/v1/2024.findings-acl.29

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.004535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 863d7b45-36b3-4102-a9f2-4199f4459204 · outbound

This paper cites Cognitive debiasing large language models for decision-making.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Cognitive debiasing large language models for decision-making

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.069580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e050b629-3438-4045-b63f-c37ceeee04fc · outbound

This paper cites A comprehensive evaluation of cognitive biases in llms.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs A comprehensive evaluation of cognitive biases in llms

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.164477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1790f765-6b5f-4bcd-ab13-31b7728058bc · outbound

This paper cites An Empirical Comparison of Instance Attribution Methods for NLP.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs An Empirical Comparison of Instance Attribution Methods for NLP

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T18:51:09.839760Z

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 3476c208-b490-4730-9b8c-8238d813e2b5 · outbound

This paper cites CBEval: A framework for evaluating and interpreting cognitive biases in LLMs.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs CBEval: A framework for evaluating and interpreting cognitive biases in LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.411906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d0bda09-1bd0-4edc-8379-faa34c4a846e · outbound

This paper cites Lora vs full fine-tuning: An illusion of equivalence.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Lora vs full fine-tuning: An illusion of equivalence

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.486428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0698612-e580-4d42-bd00-3137f2d228a3 · outbound

This paper cites Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T18:51:09.489268Z

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 d31e985b-cc8c-4ba3-a28a-773897899d6d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.654906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d008da10-c511-4d0d-b54f-3995c135a8f3 · outbound

This paper cites Language models are susceptible to incorrect patient self-diagnosis in medical applications.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Language models are susceptible to incorrect patient self-diagnosis in medical applications

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:51:09.296538Z

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 b165cee6-0b64-4a83-896a-d6d01edd8de8 · outbound

This paper cites (2024) and Itzhak et al.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs (2024) and Itzhak et al

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:11.087980Z

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 da26cc40-867b-4498-ab15-8db43f1d10ff · outbound

This paper cites Which allocation level do you choose for this purpose?.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Which allocation level do you choose for this purpose?

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:10.981097Z

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 30100a4e-4142-4037-869e-8f9ae5775098 · outbound

This paper cites These results verify that our finetuning setting is good enough to create models that can simulate fully finetuned models, especially regarding the bias score trends.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs These results verify that our finetuning setting is good enough to create models that can simulate fully finetuned models, especially regarding the bias score trends

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:10.896219Z

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 b0aca930-d8bc-4fea-9294-679e70039cc5 · outbound

This paper cites Towards understanding fine-tuning mechanisms of llms via circuit analysis.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Towards understanding fine-tuning mechanisms of llms via circuit analysis

Reference 1981

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:11.176196Z

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 f1f80435-a67e-424e-9da9-3e77e1cc164d · outbound

This paper cites Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting

Reference 1983

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.321450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a371982d-e213-4f93-aefb-d702e58b01f6 · outbound

This paper cites Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias

Reference 2011

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:51:10.261801Z

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 6e9689f5-dfcd-42ab-8e8e-a0971c7366c2 · outbound

This paper cites Addressing cognitive bias in medical language models.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Addressing cognitive bias in medical language models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:08.332503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e114f3a2-95e2-4c36-bf59-d8b12b26273f · outbound

This paper cites Isabel O.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Isabel O

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:11.377974Z

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 abb29a4c-866a-4362-a23c-f3531cf06a43 · outbound

This paper cites Explanation sensitivity to the randomness of large language models: the case of journalistic text classification.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Explanation sensitivity to the randomness of large language models: the case of journalistic text classification

Reference 2022

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:51:10.680381Z

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 28ad5ef9-28e8-42d8-80c6-3ff672449448 · outbound

This paper cites 11 Published as a conference paper at COLM 2025 Zhibo Chu, Zichong Wang, and Wenbin Zhang.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs 11 Published as a conference paper at COLM 2025 Zhibo Chu, Zichong Wang, and Wenbin Zhang

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:11.494317Z

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 20315f6b-4426-4237-b172-e0699b58a691 · outbound

This paper cites Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:06.739410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f949745f-3edd-4db8-b64f-da715164954d · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:07.530974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.