{"as_of":"2026-08-08T14:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7de490707541723a8e5f34ca5d8b6ec88e04ccd3e3dcfd8ce2e373558ee9fe9a","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T17:23:22.492228Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.10946/citation-record","integrity":"/paper/2509.10946/integrity","json":"/paper/2509.10946/citation-record.json","paper":"/paper/2509.10946"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.065688Z","title":"Tinyml: Current progress, research challenges, and future roadmap,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.065688Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:8762abd3e478bf1cab8878adfdfe6180b6d288f84b53b35a30841365e0cacc80","observation_id":"f720c7bb-1771-4d9e-85ee-a0ec2ccad408","resolution":{"observed_at":"2026-08-04T17:23:21.065688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.128045Z","title":"Edge impulse: An mlops platform for tiny machine learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.128045Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:f98cfc6742f22e1409273ba2ea16ac999cd67e00c859b887b894d7fc3c587d0c","observation_id":"2d5aef0b-10f7-4fa8-bcb7-0436e33b41f8","resolution":{"observed_at":"2026-08-04T17:23:21.128045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.169667Z","title":"Llm- based test-driven interactive code generation: User study and empirical evaluation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.169667Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:5ba29370f84c6d9e82ff3344a1ccebd0a37af69c64035359d6eb5c9d449290e4","observation_id":"c703c542-cfc1-4894-bfbd-916ccbf4ddec","resolution":{"observed_at":"2026-08-04T17:23:21.169667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.257421Z","title":"Large language models for software engineering: Sur- vey and open problems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.257421Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:028d6b9eb7777cbc17dcc2c9a3168aef722bf9ed38fb6004b154b314018f0c93","observation_id":"4e26c96d-37b8-4296-8587-52c31d49c4c1","resolution":{"observed_at":"2026-08-04T17:23:21.257421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12420","last_updated":"2025-04-05T16:29:10Z","snapshot_observed_at":"2026-08-05T15:37:40.321385Z","submitted_at":"2025-01-20T22:20:57Z","title":"Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12420","snapshot_observed_at":"2026-08-04T17:23:21.346463Z","title":"Consolidating tinyml lifecycle with large language models: Reality, illusion, or opportunity?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.346463Z"},"links":{"cited_paper":"/paper/2501.12420","citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:6d9fe186f182011484c0e9e3652f67719485eff42be4d43b3f5427931cd461ed","observation_id":"d79f3737-8a26-4f87-a256-c5735b048f05","resolution":{"observed_at":"2026-08-04T17:23:21.346463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.405766Z","title":"Towards risk-aware artificial intelligence and machine learning systems: An overview,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.405766Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:bb4de5d089f4b7e9be71fafd35646b666318be44fc1325d0b96bf443826cea25","observation_id":"ea42338a-0022-4d9e-aaf1-f8a145e664f0","resolution":{"observed_at":"2026-08-04T17:23:21.405766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12334","last_updated":"2025-08-23T18:44:57Z","snapshot_observed_at":"2026-07-06T18:32:44.452493Z","submitted_at":"2024-06-18T06:59:24Z","title":"What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12334","snapshot_observed_at":"2026-08-04T17:23:21.474317Z","title":"What did i do wrong? quantifying llms’ sensitivity and consistency to prompt engineering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.474317Z"},"links":{"cited_paper":"/paper/2406.12334","citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:9338292292741529c6a25664991ece84d47b7a250ec8695128e2f6a6ae99d916","observation_id":"658d5516-63eb-40d5-8f06-36bb65bf298a","resolution":{"observed_at":"2026-08-04T17:23:21.474317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11938","last_updated":"2023-08-31T09:02:16Z","snapshot_observed_at":"2026-07-06T15:19:13.162460Z","submitted_at":"2023-04-24T09:20:13Z","title":"Is ChatGPT the Ultimate Programming Assistant -- How far is it?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11938","snapshot_observed_at":"2026-08-04T17:23:21.574210Z","title":"Is chatgpt the ultimate programming assistant – how far is it?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.574210Z"},"links":{"cited_paper":"/paper/2304.11938","citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:7be1745871d864d6edc813836678c2cc3bd4a17e7915d3d81f3cec22f72f5386","observation_id":"1cd2bc88-95f7-4a24-928c-f98710d6afa7","resolution":{"observed_at":"2026-08-04T17:23:21.574210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.684036Z","title":"Prompt engineering in consistency and reliability with the evidence- based guideline for llms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.684036Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:402f57ca688b79a2c6000a1058943e85c60c11ac87858fff04bf03d06b3aef99","observation_id":"4f624208-ae18-4149-938b-5a352f59127b","resolution":{"observed_at":"2026-08-04T17:23:21.684036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.793825Z","title":"Mindmap: constructing evidence chains for multi-step reasoning in large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.793825Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:1cf583a06f353a35f6595390229dbc6bc7bee794c2c99c78f74711a26ea5da6b","observation_id":"d9e77b84-f0fd-49c4-939b-6c18bc8b8ce4","resolution":{"observed_at":"2026-08-04T17:23:21.793825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.882528Z","title":"Morepair: Teaching llms to repair code via multi- objective fine-tuning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.882528Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:c7c116343156db9bd923705b41f679be4f86e3b72277488a072e6ed4b7e7f556","observation_id":"da704453-7066-4314-b607-7b9b012a48ab","resolution":{"observed_at":"2026-08-04T17:23:21.882528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:21.959243Z","title":"The patch overfitting problem in automated program repair: Practical magnitude and a baseline for realistic benchmarking,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:21.959243Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:e9a6c2fa24ac61887bacda7ba8b91523651b789421b0dbb6547a0a1a68053cd8","observation_id":"5954333d-adbc-4857-b55e-b18c73e29984","resolution":{"observed_at":"2026-08-04T17:23:21.959243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:22.014815Z","title":"Challenges and opportunities in integrating llms into con- tinuous integration/continuous deployment (ci/cd) pipelines,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:22.014815Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:0ff2eb0a9c1f4e134e31d72956ff9d303646f29f36d0d806999cd7d3760cdd6b","observation_id":"0c473680-8a6c-4bd9-9b6b-04dd89679433","resolution":{"observed_at":"2026-08-04T17:23:22.014815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:22.079098Z","title":"Bugs in large language models generated code: An empirical study,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:22.079098Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:fbc115feb4953b21e611f8e690d5d86749bf3c1b924638b0ade5029e10c69a1d","observation_id":"a9b16056-dc69-4453-86c7-8c8bde8e7295","resolution":{"observed_at":"2026-08-04T17:23:22.079098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:22.193205Z","title":"Vecogen: Automating generation of formally verified c code with large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:22.193205Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:69a6dce499e864da43d17e0ccaf742d8083b4ca3b404c430a647e9f33b84b0ef","observation_id":"9ab97865-288c-4d58-8138-607ace102654","resolution":{"observed_at":"2026-08-04T17:23:22.193205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-05T17:55:26.008016Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-04T17:23:22.285628Z","title":"A systematic survey of prompt engineering in large language models: Techniques and applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:22.285628Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:6384cb1c5576ad38d0268cc8f32c06ceb7ac784d673882e3b6285117611c0a60","observation_id":"381c8924-3661-4e80-9830-b5fbfd9fc151","resolution":{"observed_at":"2026-08-04T17:23:22.285628Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.13948","last_updated":"2025-08-19T15:37:29Z","snapshot_observed_at":"2026-08-05T18:53:31.383828Z","submitted_at":"2025-08-19T15:37:29Z","title":"Prompt Orchestration Markup Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.13948","snapshot_observed_at":"2026-08-04T17:23:22.391430Z","title":"Prompt orchestration markup language,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:22.391430Z"},"links":{"cited_paper":"/paper/2508.13948","citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:eeb2b00906bb54effc017c60f671e20f2a8b4c0613ab36faf5efd5874a74ec71","observation_id":"f10feb27-682a-4b6f-88c0-0d0f5dc03bdf","resolution":{"observed_at":"2026-08-04T17:23:22.391430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:23:22.492228Z","title":"Lorp: Llm-based logical reasoning via prolog,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T17:23:22.492228Z"},"links":{"citing_paper":"/paper/2509.10946"},"observation_digest":"sha256:d3a9a6161fda6a0b0c4afe40ca2dcc2d9f5dd24e7fdfb35a888c78e32ccced8c","observation_id":"bd0f73e1-31c2-4327-9f3d-12a3423266b5","resolution":{"observed_at":"2026-08-04T17:23:22.492228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.10946","last_updated":"2025-09-13T19:00:04Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-04T17:23:20.537876Z","submitted_at":"2025-09-13T19:00:04Z","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":18},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"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."}