Pith. sign in

Paper Citation Record · LEDGER

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning

As of 8 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2509.10946.

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

pith.paper-citation-record.v1
2509.10946 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:23:22.492228Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

18 of 18 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved18
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f720c7bb-1771-4d9e-85ee-a0ec2ccad408 · outbound

This paper cites Tinyml: Current progress, research challenges, and future roadmap,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Tinyml: Current progress, research challenges, and future roadmap,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.065688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.065688Z digest=sha256:8762abd3e478bf1cab8878adfdfe6180b6d288f84b53b35a30841365e0cacc80

Observation 2d5aef0b-10f7-4fa8-bcb7-0436e33b41f8 · outbound

This paper cites Edge impulse: An mlops platform for tiny machine learning,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Edge impulse: An mlops platform for tiny machine learning,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.128045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.128045Z digest=sha256:f98cfc6742f22e1409273ba2ea16ac999cd67e00c859b887b894d7fc3c587d0c

Observation c703c542-cfc1-4894-bfbd-916ccbf4ddec · outbound

This paper cites Llm- based test-driven interactive code generation: User study and empirical evaluation,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Llm- based test-driven interactive code generation: User study and empirical evaluation,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.169667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.169667Z digest=sha256:5ba29370f84c6d9e82ff3344a1ccebd0a37af69c64035359d6eb5c9d449290e4

Observation 4e26c96d-37b8-4296-8587-52c31d49c4c1 · outbound

This paper cites Large language models for software engineering: Sur- vey and open problems,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Large language models for software engineering: Sur- vey and open problems,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.257421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.257421Z digest=sha256:028d6b9eb7777cbc17dcc2c9a3168aef722bf9ed38fb6004b154b314018f0c93

Observation d79f3737-8a26-4f87-a256-c5735b048f05 · outbound

This paper cites Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.346463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.346463Z digest=sha256:6d9fe186f182011484c0e9e3652f67719485eff42be4d43b3f5427931cd461ed

Observation ea42338a-0022-4d9e-aaf1-f8a145e664f0 · outbound

This paper cites Towards risk-aware artificial intelligence and machine learning systems: An overview,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Towards risk-aware artificial intelligence and machine learning systems: An overview,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.405766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.405766Z digest=sha256:bb4de5d089f4b7e9be71fafd35646b666318be44fc1325d0b96bf443826cea25

Observation 658d5516-63eb-40d5-8f06-36bb65bf298a · outbound

This paper cites What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.474317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.474317Z digest=sha256:9338292292741529c6a25664991ece84d47b7a250ec8695128e2f6a6ae99d916

Observation 1cd2bc88-95f7-4a24-928c-f98710d6afa7 · outbound

This paper cites Is ChatGPT the Ultimate Programming Assistant -- How far is it?.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Is ChatGPT the Ultimate Programming Assistant -- How far is it?

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.574210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.574210Z digest=sha256:7be1745871d864d6edc813836678c2cc3bd4a17e7915d3d81f3cec22f72f5386

Observation 4f624208-ae18-4149-938b-5a352f59127b · outbound

This paper cites Prompt engineering in consistency and reliability with the evidence- based guideline for llms,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Prompt engineering in consistency and reliability with the evidence- based guideline for llms,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.684036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.684036Z digest=sha256:402f57ca688b79a2c6000a1058943e85c60c11ac87858fff04bf03d06b3aef99

Observation d9e77b84-f0fd-49c4-939b-6c18bc8b8ce4 · outbound

This paper cites Mindmap: constructing evidence chains for multi-step reasoning in large language models,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Mindmap: constructing evidence chains for multi-step reasoning in large language models,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.793825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.793825Z digest=sha256:1cf583a06f353a35f6595390229dbc6bc7bee794c2c99c78f74711a26ea5da6b

Observation da704453-7066-4314-b607-7b9b012a48ab · outbound

This paper cites Morepair: Teaching llms to repair code via multi- objective fine-tuning,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Morepair: Teaching llms to repair code via multi- objective fine-tuning,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.882528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.882528Z digest=sha256:c7c116343156db9bd923705b41f679be4f86e3b72277488a072e6ed4b7e7f556

Observation 5954333d-adbc-4857-b55e-b18c73e29984 · outbound

This paper cites The patch overfitting problem in automated program repair: Practical magnitude and a baseline for realistic benchmarking,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning The patch overfitting problem in automated program repair: Practical magnitude and a baseline for realistic benchmarking,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:21.959243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:21.959243Z digest=sha256:e9a6c2fa24ac61887bacda7ba8b91523651b789421b0dbb6547a0a1a68053cd8

Observation 0c473680-8a6c-4bd9-9b6b-04dd89679433 · outbound

This paper cites Challenges and opportunities in integrating llms into con- tinuous integration/continuous deployment (ci/cd) pipelines,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Challenges and opportunities in integrating llms into con- tinuous integration/continuous deployment (ci/cd) pipelines,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:22.014815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:22.014815Z digest=sha256:0ff2eb0a9c1f4e134e31d72956ff9d303646f29f36d0d806999cd7d3760cdd6b

Observation a9b16056-dc69-4453-86c7-8c8bde8e7295 · outbound

This paper cites Bugs in large language models generated code: An empirical study,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Bugs in large language models generated code: An empirical study,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:22.079098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:22.079098Z digest=sha256:fbc115feb4953b21e611f8e690d5d86749bf3c1b924638b0ade5029e10c69a1d

Observation 9ab97865-288c-4d58-8138-607ace102654 · outbound

This paper cites Vecogen: Automating generation of formally verified c code with large language models,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Vecogen: Automating generation of formally verified c code with large language models,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:22.193205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:22.193205Z digest=sha256:69a6dce499e864da43d17e0ccaf742d8083b4ca3b404c430a647e9f33b84b0ef

Observation 381c8924-3661-4e80-9830-b5fbfd9fc151 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:22.285628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:22.285628Z digest=sha256:6384cb1c5576ad38d0268cc8f32c06ceb7ac784d673882e3b6285117611c0a60

Observation f10feb27-682a-4b6f-88c0-0d0f5dc03bdf · outbound

This paper cites Prompt Orchestration Markup Language.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Prompt Orchestration Markup Language

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:22.391430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:22.391430Z digest=sha256:eeb2b00906bb54effc017c60f671e20f2a8b4c0613ab36faf5efd5874a74ec71

Observation bd0f73e1-31c2-4327-9f3d-12a3423266b5 · outbound

This paper cites Lorp: Llm-based logical reasoning via prolog,.

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning Lorp: Llm-based logical reasoning via prolog,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T17:23:22.492228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:23:22.492228Z digest=sha256:d3a9a6161fda6a0b0c4afe40ca2dcc2d9f5dd24e7fdfb35a888c78e32ccced8c

Pith citing papers

No inbound Pith citation observations are available.