Paper Citation Record · LEDGER

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks

As of 23 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2507.23146.

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

pith.paper-citation-record.v1
2507.23146 v4

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T11:06:08.015456Z

measured 41 of 41 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 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

41 of 41 outbound references displayed

verified exact6
verified fuzzy23
unresolved8
parse uncertain0
malformed identifier2
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d54002f8-0522-4c64-82c3-6fc6fa672aac · outbound

This paper cites Advances in Electronic Phenotyping: From Rule-Based Definitions to Machine Learning Models.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Advances in Electronic Phenotyping: From Rule-Based Definitions to Machine Learning Models

Reference 1

Resolution: malformed identifier; doi_truncated, observed 2026-08-06T11:06:09.261423Z

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 5e62f23b-f03b-4b46-be2f-432198371a61 · outbound

This paper cites Towards automated phenotype definition extraction using large language models.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Towards automated phenotype definition extraction using large language models

Reference 2

Resolution: verified exact; doi, observed 2026-08-06T11:06:09.037740Z

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 ecce1537-4bc9-4df4-a0ef-6e49733c6165 · outbound

This paper cites Making work visible for electronic phenotype implementation: Lessons learned from the eMERGE network.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Making work visible for electronic phenotype implementation: Lessons learned from the eMERGE network

Reference 3

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T11:06:09.737003Z

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 60002c1c-ee0a-45fe-b3ce-cf618ee97445 · outbound

This paper cites A general framework for developing computable clinical phenotype algorithms.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks A general framework for developing computable clinical phenotype algorithms

Reference 4

Resolution: verified exact; doi, observed 2026-08-06T11:06:08.810249Z

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 3e8d64af-19ab-4855-86b7-148a74d8cde3 · outbound

This paper cites SHREC: A framework for advancing next-generation computational phenotyping with large language models.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks SHREC: A framework for advancing next-generation computational phenotyping with large language models

Reference 5

Resolution: verified exact; doi, observed 2026-08-06T11:06:08.636195Z

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 0a146695-c30c-4ffe-99bb-97119e4c1640 · outbound

This paper cites Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond

Reference 6

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T11:06:09.489695Z

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 b616fc55-cd06-4d26-aa42-b5ff3b0a8acf · outbound

This paper cites Deductive Verification of Chain-of- Thought Reasoning.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Deductive Verification of Chain-of- Thought Reasoning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.822496Z

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 7d356364-cca8-44a5-952a-e662e2c37094 · outbound

This paper cites Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:06.741394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abda25da-8ce7-42d6-8127-16a5f79c8862 · outbound

This paper cites Large language models can be easily distracted by irrelevant context.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Large language models can be easily distracted by irrelevant context

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.813349Z

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 ecb8e2b1-4c21-4515-bfb6-8dfb8bea19a6 · outbound

This paper cites Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.804372Z

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 b8782a17-710c-4bf8-9506-823e92a9e840 · outbound

This paper cites Language Models Are Greedy Reasoners.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Language Models Are Greedy Reasoners

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.794725Z

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 b8b0937b-036d-4321-8968-deee035c40ce · outbound

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

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.785754Z

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 5b9ef066-84a6-4d58-9623-7783d4479da1 · outbound

This paper cites Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.777191Z

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 3184707f-4722-46b9-90f4-3ff422920433 · outbound

This paper cites Chain-of- Thought Reasoning in the Wild is not Always Faithful.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Chain-of- Thought Reasoning in the Wild is not Always Faithful

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.767840Z

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 ef73b372-82cc-494e-bfc6-1fdb4ff1aad1 · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Reasoning Models Don't Always Say What They Think

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.060768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f52cf14-0354-4663-9143-5919abe82b67 · outbound

This paper cites [cited 2025 Jun 10].

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks [cited 2025 Jun 10]

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.758678Z

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 024f890d-d398-4dd5-8c37-feb8dc44ad1d · outbound

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

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 f893180c-571f-442e-9f2e-92dc02c39bad · outbound

This paper cites PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.749502Z

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 891c4f96-23b5-4df3-b540-349cd65ad081 · outbound

This paper cites Rule-Based Cohort Definitions for Acute Respiratory Failure: Electronic Phenotyping Algorithm.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Rule-Based Cohort Definitions for Acute Respiratory Failure: Electronic Phenotyping Algorithm

Reference 19

Resolution: malformed identifier; no resolver link, observed 2026-08-06T11:06:07.220218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 123c2014-cb64-4304-b7a1-370b2f64a11e · outbound

This paper cites The eICU Collaborative Research Database, a freely available multi-center database for critical care research.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks The eICU Collaborative Research Database, a freely available multi-center database for critical care research

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.263225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b02f6982-1d95-44ce-ac39-6fdde679ab57 · outbound

This paper cites Ollama; 2024 [cited 2024 Dec 18].

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Ollama; 2024 [cited 2024 Dec 18]

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.629792Z

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 7778794b-f615-4645-9215-924a56d0266a · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.310546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d48fb61-40d5-4023-a5ab-870f5cdf9f9e · outbound

This paper cites Interrater reliability: the kappa statistic.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Interrater reliability: the kappa statistic

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.476809Z

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 4bddb60d-a483-4e33-b631-11d2be39d3cb · outbound

This paper cites Emergent Abilities of Large Language Models.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Emergent Abilities of Large Language Models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.353567Z

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 da6d56fd-43bf-4ae9-b22c-afc316fc28a2 · outbound

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

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks ReAct: Synergizing Reasoning and Acting in Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.424864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5cbca71-b2bf-4625-ac33-4dee552f2ab7 · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.153034Z

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 69bb715c-ee4a-479f-acbe-59de0fd428f0 · outbound

This paper cites Large language models are zero-shot reasoners.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Large language models are zero-shot reasoners

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:11.061431Z

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 1056e776-a356-423a-997c-8a9764e62143 · outbound

This paper cites Large Language Models Still Can’t Plan (A Benchmark for LLMs on Planning and Reasoning about Change).

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Large Language Models Still Can’t Plan (A Benchmark for LLMs on Planning and Reasoning about Change)

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.960175Z

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 c2544d17-6930-4b8d-88d5-f83cfb1cdac9 · outbound

This paper cites GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.559969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 888dab80-b151-4868-8594-17139b86394a · outbound

This paper cites A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [Internet].

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [Internet]

Reference 30

Resolution: verified exact; doi, observed 2026-08-06T11:06:08.423912Z

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 fa68a6f3-8dcf-4edf-8fa5-97cb8720bf9d · outbound

This paper cites LLM-based agentic systems in medicine and healthcare.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks LLM-based agentic systems in medicine and healthcare

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.642134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3afde07-30b4-4c87-9655-91f2c8b96af5 · outbound

This paper cites Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models [Internet].

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models [Internet]

Reference 32

Resolution: verified exact; doi, observed 2026-08-06T11:06:08.277622Z

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 3edaae83-e511-42fa-9c1c-11e2599f7b9f · outbound

This paper cites Understanding Reasoning in Thinking Language Models via Steering Vectors.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Understanding Reasoning in Thinking Language Models via Steering Vectors

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.802590Z

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 4807b643-07c5-47b0-9b0d-a06a4faff031 · outbound

This paper cites Transformer Circuits [Internet].

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Transformer Circuits [Internet]

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.695705Z

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 9914b539-2384-4531-91b6-7ef5e1c56318 · outbound

This paper cites Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.565561Z

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 fcfb08dd-3b77-4e4b-a4ce-7492b59e8e6f · outbound

This paper cites Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.443518Z

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 b1ab383c-93a7-4d8e-85fb-177e7e7fc905 · outbound

This paper cites A Methodology for Generating and Optimizing Chain-of-Thought Based on Knowledge Graphs.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks A Methodology for Generating and Optimizing Chain-of-Thought Based on Knowledge Graphs

Reference 37

Resolution: verified exact; doi, observed 2026-08-06T11:06:08.130096Z

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 ed20780e-9f5f-4627-ab4f-07f56ea36138 · outbound

This paper cites Training language models to follow instructions with human feedback.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Training language models to follow instructions with human feedback

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.322042Z

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 5dbf6a72-a40e-4f07-bcc7-ac3a419b23c0 · outbound

This paper cites STaR: Bootstrapping Reasoning With Reasoning.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks STaR: Bootstrapping Reasoning With Reasoning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:10.189166Z

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 20faaa8f-1841-409f-b20a-4059bee80af7 · outbound

This paper cites Leap-of-thought: teaching pre-trained models to systematically reason over implicit knowledge.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Leap-of-thought: teaching pre-trained models to systematically reason over implicit knowledge

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:09.967053Z

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 136d5028-6b67-4198-b405-940d93b9e715 · outbound

This paper cites On contrastive learning for likelihood-free inference.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks On contrastive learning for likelihood-free inference

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:06:09.853077Z

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.

Pith citing papers

No inbound Pith citation observations are available.