Paper Citation Record · LEDGER

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows

As of 22 July 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2604.18038.

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

pith.paper-citation-record.v1
2604.18038 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T03:47:54.377400Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-20T06:30:07.809122+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

42 of 42 outbound references displayed

verified exact6
verified fuzzy31
unresolved3
parse uncertain1
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8240aa9e-dd4e-401a-8d4f-469251b9a577 · outbound

This paper cites an unresolved cited work.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-22T14:41:42.870219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation d7c13606-bbb2-4ef1-866c-3409f7db42b7 · outbound

This paper cites an unresolved cited work.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-22T14:41:42.884818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 02c199ac-32b9-4bf7-b52f-e8041833ef64 · outbound

This paper cites an unresolved cited work.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-22T14:41:42.878148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 2d4a488e-13d9-44e1-b18d-50ade819ad85 · outbound

This paper cites A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:21:06.147028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 9252e22c-c572-49be-9b27-99f10a158497 · outbound

This paper cites Large language models in healthcare and medical domain: A review.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Large language models in healthcare and medical domain: A review

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.874758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 62ab7807-cd75-4808-88fd-bfadfa5d64e0 · outbound

This paper cites Large language models in medical and healthcare fields: applications, advances, and challenges.Artificial intelligence review, 57(11):299.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Large language models in medical and healthcare fields: applications, advances, and challenges.Artificial intelligence review, 57(11):299

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.903171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 71665d65-89b5-4eea-9971-876481d84ebe · outbound

This paper cites LLMs-Healthcare : Current Applications and Challenges of Large Language Models in various Medical Specialties.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows LLMs-Healthcare : Current Applications and Challenges of Large Language Models in various Medical Specialties

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:21:06.185024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 4734798e-baf2-421d-97b4-6526a5129367 · outbound

This paper cites Race, gender, and age biases in biomedical masked language models.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Race, gender, and age biases in biomedical masked language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.892575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 86a40e79-3170-4f26-bf28-b59bcb443543 · outbound

This paper cites Unmasking and quantifying racial bias of large language models in medical report generation.Communications medicine, 4(1):176.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Unmasking and quantifying racial bias of large language models in medical report generation.Communications medicine, 4(1):176

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.900034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 7068753b-6cc2-4bd7-9e60-7775a3f03e78 · outbound

This paper cites Assessing racial and ethnic bias in text generation for healthcare-related tasks by chatgpt1.MedRxiv.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Assessing racial and ethnic bias in text generation for healthcare-related tasks by chatgpt1.MedRxiv

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.888618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 41aa464a-e5ac-492e-94c4-58678be62560 · outbound

This paper cites Measuring Implicit Bias in Explicitly Unbiased Large Language Models.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Measuring Implicit Bias in Explicitly Unbiased Large Language Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:21:06.207413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 8934172c-0b8b-4fc4-b02e-56bd64d781b1 · outbound

This paper cites Apakama, Carol R.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Apakama, Carol R

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.896036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 4f83bfdb-1cbc-405a-8525-9f2ef2867ed0 · outbound

This paper cites Assessing the potential of gpt-4 to perpetuate racial and gender biases in health care: a model evaluation study.The Lancet Digital Health, 6(1):e12–e22.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Assessing the potential of gpt-4 to perpetuate racial and gender biases in health care: a model evaluation study.The Lancet Digital Health, 6(1):e12–e22

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.881732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation cedb1dee-6c1e-49f1-873b-ec6a4f60a0f1 · outbound

This paper cites An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:21:06.107898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 675ffaf5-105f-4e00-973e-b46dfab105cc · outbound

This paper cites Search-o1: Agentic search-enhanced large reasoning models.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Search-o1: Agentic search-enhanced large reasoning models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.856881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 8ed472e6-526a-40ec-83c0-1a1b0302c87b · outbound

This paper cites Using flowise to streamline biomedical data discovery and analysis.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Using flowise to streamline biomedical data discovery and analysis

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.850148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation b2c98390-56f4-4111-be9a-5af45e8a400f · outbound

This paper cites gpt4_bias: Assessing gpt-4’s potential for perpetuating racial and gender biases in healthcare.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows gpt4_bias: Assessing gpt-4’s potential for perpetuating racial and gender biases in healthcare

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.793261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation d6c7378c-033c-43c5-9c3e-74d05bc344c1 · outbound

This paper cites Advancement of engineered bacteria for orally delivered therapeutics.Small, 19(48):2302702.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Advancement of engineered bacteria for orally delivered therapeutics.Small, 19(48):2302702

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.810030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 4f424d44-ecf5-4e83-be58-b929662303b6 · outbound

This paper cites Review on the coronavirus disease (covid-19) pandemic: its outbreak and current status.International journal of clinical practice, 74(11):e13637.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Review on the coronavirus disease (covid-19) pandemic: its outbreak and current status.International journal of clinical practice, 74(11):e13637

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.840363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation e2ab734f-129f-45f9-87d1-861bb40694fa · outbound

This paper cites Causes, symptoms and treatments common hepatitis b today.Pharmacognosy Journal, 13(3).

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Causes, symptoms and treatments common hepatitis b today.Pharmacognosy Journal, 13(3)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.806759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 4a3fc1a4-5a5e-43ff-81e2-0e92a3fcfa05 · outbound

This paper cites Protecting the confidence of hiv patients and the role of nurses.European Chemical Bulletin.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Protecting the confidence of hiv patients and the role of nurses.European Chemical Bulletin

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.863296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 3f6555d4-798c-4e7d-807f-7d824decd0d4 · outbound

This paper cites The epidemic of tuberculosis on vaccinated population.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows The epidemic of tuberculosis on vaccinated population

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.789497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 0bee04a3-b681-405f-ae88-d6edbbfcbc0d · outbound

This paper cites A review on diabetes mellitus-an annihilatory metabolic disorder.Journal of Pharmaceutical Sciences and Research, 12(2):232–235.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows A review on diabetes mellitus-an annihilatory metabolic disorder.Journal of Pharmaceutical Sciences and Research, 12(2):232–235

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.797342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 405010ee-2293-4e47-81d5-496e5e4f1511 · outbound

This paper cites Il-1β in neoplastic disease and the role of its tumor-derived form in the progression and treatment of metastatic prostate cancer.Cancers, 17(2):290.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Il-1β in neoplastic disease and the role of its tumor-derived form in the progression and treatment of metastatic prostate cancer.Cancers, 17(2):290

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.837342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation c8b46708-dc69-4cff-aa96-3b69feee9a6e · outbound

This paper cites The role of interleukin-10 in autoimmune disease: systemic lupus erythematosus (sle) and multiple sclerosis (ms).Cytokine & growth factor reviews, 13(4-5):403– 412.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows The role of interleukin-10 in autoimmune disease: systemic lupus erythematosus (sle) and multiple sclerosis (ms).Cytokine & growth factor reviews, 13(4-5):403– 412

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.846661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation ba20a358-aa13-4821-a722-6ddd5977b688 · outbound

This paper cites Sarcoidosis as an autoimmune disease.Frontiers in immunology, 10:2933.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Sarcoidosis as an autoimmune disease.Frontiers in immunology, 10:2933

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.843765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation f6b02e35-243e-4fcb-b33e-fa401f966df7 · outbound

This paper cites Exploring deepseek: A survey on advances, applications, challenges and future directions.IEEE/CAA Journal of Automatica Sinica, 12(5):872–893.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Exploring deepseek: A survey on advances, applications, challenges and future directions.IEEE/CAA Journal of Automatica Sinica, 12(5):872–893

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.833865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 22c69aa8-da73-42c2-b014-f864f17fc817 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows On the Opportunities and Risks of Foundation Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:21:06.083671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 6a1415e8-4082-45cf-a4ea-ad53bda88d4d · outbound

This paper cites Human-Centric Evaluation for Foundation Models.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Human-Centric Evaluation for Foundation Models

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:21:06.094847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 48ba79c1-50f2-4356-a57b-17a4e5546a82 · outbound

This paper cites A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:21:06.130490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 7279715c-52c0-48fd-87c3-df043a1e941a · outbound

This paper cites Vertex ai platform.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Vertex ai platform

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.800635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation f3ee10c1-11da-484e-9a55-291d53e90d20 · outbound

This paper cites Azure ai foundry.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Azure ai foundry

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.822201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 34da28b5-6b85-4443-935d-c3e6f19c6e6d · outbound

This paper cites Flowise documentation.https://docs.flowiseai.com/.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Flowise documentation.https://docs.flowiseai.com/

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.866658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 204d8d74-1bd5-45bf-bacc-9809125eb9f3 · outbound

This paper cites Brave search api.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Brave search api

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.812959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 6c48f2bf-a7cf-479f-ae6f-51fd33f19ffc · outbound

This paper cites Openai platform.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Openai platform

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.815893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 104b6d27-d556-4c74-b26d-e7f5e192360e · outbound

This paper cites Pinecone (vector database) on azure marketplace.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Pinecone (vector database) on azure marketplace

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.819125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 58dbbbe2-efbb-41a5-87b0-1d3c2404fcb8 · outbound

This paper cites an unresolved cited work.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Unresolved cited work

Reference 37

Resolution: parse uncertain; raw_fallback, observed 2026-05-22T14:41:42.803614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 0b6327ee-d999-4277-8a8f-d70ca68226f7 · outbound

This paper cites Supabase: The postgres development platform.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Supabase: The postgres development platform

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.853423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 1788571a-9991-4940-8296-5004f5111ae2 · outbound

This paper cites Enhancing medical ai with retrieval-augmented generation: A mini narrative review.Digital health, 11:20552076251337177.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Enhancing medical ai with retrieval-augmented generation: A mini narrative review.Digital health, 11:20552076251337177

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.859878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 06e3ed00-cc05-4b8f-a681-1a931d337155 · outbound

This paper cites Controlling the false discovery rate: A practical and powerful approach to multiple testing.Journal of the Royal Statistical Society: Series B (Methodological), 57(1):289–300.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Controlling the false discovery rate: A practical and powerful approach to multiple testing.Journal of the Royal Statistical Society: Series B (Methodological), 57(1):289–300

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.825963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 684ef8ab-79e2-4829-b380-87daff97e5a5 · outbound

This paper cites Mann–whitney u test and kruskal–wallis h test statistics in r.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Mann–whitney u test and kruskal–wallis h test statistics in r

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.829238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 06bcfd17-dcd7-4fac-927f-adee9c8514f8 · outbound

This paper cites Enhancing-llm-driven-bias-detection-in-healthcare-agentic-workflows-for-racial-disparity-mitigation.

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows Enhancing-llm-driven-bias-detection-in-healthcare-agentic-workflows-for-racial-disparity-mitigation

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T14:41:42.785343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Pith citing papers

No inbound Pith citation observations are available.