Pith. sign in

Paper Citation Record · LEDGER

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs

As of 7 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2607.22555.

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

pith.paper-citation-record.v1
2607.22555 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T13:38:12.283001Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

15 of 15 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved15
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a6a161bd-6c81-4ef9-b4c0-699d6fbc74f3 · outbound

This paper cites an unresolved cited work.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Unresolved cited work

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:10.943160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:10.943160Z digest=sha256:c809f8f503f55e3f960e23423be5b83865a4954fac876fd6a39af34fe566eb9f

Observation 2b915634-11be-4928-a0b2-c5d593c04f55 · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.119917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.119917Z digest=sha256:3bdf8729957afb9af5a0dcea51d285e0acbef065e2309c0b9f00369ce48d5be9

Observation fbbe7ad0-62de-42bd-a871-203c3e9afd2d · outbound

This paper cites DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.263118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.263118Z digest=sha256:1e63464bc1b23bb624527091a210f471ccb19ff5718325c64bbf4544c59a8306

Observation 4d99bf37-1627-4e4c-958e-ef67a3cf2ea3 · outbound

This paper cites URL: https://arxiv.org/abs/2511.23269.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs URL: https://arxiv.org/abs/2511.23269

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.397236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.397236Z digest=sha256:94979404c3ef47bd074e21368e8d81c37a24c57e1c122571b5cd36faea4a8e69

Observation 2d9747f1-83ab-435e-a42a-1e7ce2b0e03b · outbound

This paper cites Kocaman, et al., Clinical large language model evaluation by expert review (clever), JMIR AI 4 (2025) e72153.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Kocaman, et al., Clinical large language model evaluation by expert review (clever), JMIR AI 4 (2025) e72153

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.536964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.536964Z digest=sha256:2a29863f06975195444d20c452dc75565a885d1c6e0fff8161ad0f624453f115

Observation 04bd3213-fb3a-4c7c-8374-4d2a35f511ad · outbound

This paper cites Singhal, et al., Large language models encode clinical knowledge, Nature (2023).

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Singhal, et al., Large language models encode clinical knowledge, Nature (2023)

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.620400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.620400Z digest=sha256:d3e1937171a6d3f95a384e74e1370d6cdfee7e0a4fdf2a8154bdc6ac704ca99f

Observation cfc5b7cf-fac8-4f3e-ac5d-8da6fe0720f9 · outbound

This paper cites URL: https://www.nature.com/articles/s41591-024-03423-7.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs URL: https://www.nature.com/articles/s41591-024-03423-7

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.750964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.750964Z digest=sha256:5fb763f216e0659b9fb1574e58d5d0bf3df43148da72e1943f08c5f5e7abc787

Observation ea9593bb-f474-4e0e-9d9d-568a23ab9391 · outbound

This paper cites Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.801917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.801917Z digest=sha256:abe1b52acf5f44dbb12159ab9b3f03647fedac9611c1ec888ae50c7843c43b69

Observation 09721287-5f9a-4dec-80e6-c864a7798e6c · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.901477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.901477Z digest=sha256:ccc4a584fccf6d28647134c863d07d2ce890851f800b7ccb4c11ff30d3e4f48a

Observation 69b5d50b-427f-4ebe-8a07-e0a582e73bf3 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.972016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.972016Z digest=sha256:dc48b98e45bbb309ad1b029d842e871c7c88479e3df9da8fb0b8ef349d6fc56e

Observation eb8a77f0-b144-4654-bdff-6d96022e04fd · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs ReAct: Synergizing Reasoning and Acting in Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:12.033056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:12.033056Z digest=sha256:2515e464629722474422996c04259d58d276a85e2b99bc2df89c7cbb60bfebb5

Observation f03d9c25-ee3a-420f-8d9a-1f3e5a192ae6 · outbound

This paper cites Augmented Language Models: a Survey.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Augmented Language Models: a Survey

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:12.099740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:12.099740Z digest=sha256:592112a7b60d46261004cf3b4a898e29736bc3aa340bd0d4011d288aada25c91

Observation 58ef1819-44d5-4646-bb48-ca8109f518e0 · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:12.205520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:12.205520Z digest=sha256:78639e9671e97efbbe90c251f22c1e5964bde68d7ae6960fa131984779751cb5

Observation c1fd0faa-9596-49a3-83ea-ddbc79784053 · outbound

This paper cites Survey of Hallucination in Natural Language Generation.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Survey of Hallucination in Natural Language Generation

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:12.283001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:12.283001Z digest=sha256:8c6425f02ff8d562ea464725b7a82dfbbd3cb89f5b6b8305dba47e0374904728

Observation 702d8df1-7e43-4e65-ab43-a2aceccb29d4 · outbound

This paper cites an unresolved cited work.

DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs Unresolved cited work

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-02T13:38:11.013161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:38:11.013161Z digest=sha256:11a9b253ee50377b1a0f27e281073da3c11f9f2df2e9a5b24cd191bd4bc9a2ea

Pith citing papers

No inbound Pith citation observations are available.