Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T15:29:36.610491Z
Paper Citation Record · LEDGER
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads
As of 4 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2604.12301.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-12T05:14:41.315225Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
24 of 24 outbound references displayed
- verified exact9
- verified fuzzy12
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation dcb36fcd-88bf-4f8c-9349-98a38ceae22a · outbound
This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T10:26:01.815954Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 356e53bb-114d-4a33-8461-593375aef084 · outbound
This paper cites Prompt caching with Claude.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Prompt caching with Claude
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.376381Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8862d6fc-3b64-491e-bc66-a5a933206425 · outbound
This paper cites Model context protocol specification.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Model context protocol specification
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.343062Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4f03e472-b328-47d4-8d00-4120b95a7337 · outbound
This paper cites LongBench: A bilingual, multitask benchmark for long context understanding.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads LongBench: A bilingual, multitask benchmark for long context understanding
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.350061Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 83f38bb9-3509-429d-a940-c7fb04edf6ed · outbound
This paper cites GPTCache: An open-source semantic cache for LLM applications enabling faster answers and cost savings.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads GPTCache: An open-source semantic cache for LLM applications enabling faster answers and cost savings
Reference 5
- Resolution
- verified exact
- doi, observed 2026-05-10T15:30:32.436098Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 30ee5364-978c-40da-95eb-15874edea48d · outbound
This paper cites Lee, Deming Chen, and Tri Dao.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Lee, Deming Chen, and Tri Dao
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.373560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 972bd370-8d43-49fa-97de-235fce4148cb · outbound
This paper cites FrugalGPT: How to use large language models while reducing cost and improving performance.Transactions on Machine Learning Research.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads FrugalGPT: How to use large language models while reducing cost and improving performance.Transactions on Machine Learning Research
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.363753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c96bbce6-4324-4413-8cf3-1be9bbf4d288 · outbound
This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:56:45.568475Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1afc6054-208e-4d7d-ae9f-7584c496d4a0 · outbound
This paper cites Gemma: Open Models Based on Gemini Research and Technology.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Gemma: Open Models Based on Gemini Research and Technology
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T10:26:01.811647Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9f86ba6f-52f6-4b8a-943c-59307cf49861 · outbound
This paper cites The Llama 3 Herd of Models.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads The Llama 3 Herd of Models
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T10:26:01.764284Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7587500b-1108-4ddf-af3a-e3e104fad664 · outbound
This paper cites LLMLingua: Com- pressing prompts for accelerated inference of large language models.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads LLMLingua: Com- pressing prompts for accelerated inference of large language models
Reference 11
- Resolution
- verified exact
- doi, observed 2026-05-10T15:30:32.438379Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8cca1ce9-1868-4b7e-8533-448adab09c79 · outbound
This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.370702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a850a32a-c7be-4ad1-bdd2-aa197ea472fb · outbound
This paper cites Fast inference from transformers via speculative decoding.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Fast inference from transformers via speculative decoding
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.335881Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 29f15dab-1af0-462c-b820-66479b6988c3 · outbound
This paper cites Retrieval-augmented generation for knowledge-intensive NLP tasks.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Retrieval-augmented generation for knowledge-intensive NLP tasks
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.353363Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation aa709e96-19b6-459a-b076-09cd16aed5e1 · outbound
This paper cites Large Language Model-Based Agents for Software Engineering: A Survey.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Large Language Model-Based Agents for Software Engineering: A Survey
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T12:35:49.024248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fda3e460-b468-4d0a-b8f4-abe6a7ab3b69 · outbound
This paper cites Small Language Models: Survey, Measurements, and Insights.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Small Language Models: Survey, Measurements, and Insights
Reference 16
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.780655Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 984fa1eb-ce55-47d3-aada-3a175e816e2b · outbound
This paper cites Ollama: Get up and running with large language models locally.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Ollama: Get up and running with large language models locally
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.356704Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 019e1d40-c81d-471d-9520-e1c42cf61e2d · outbound
This paper cites RouteLLM: Learning to Route LLMs with Preference Data.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads RouteLLM: Learning to Route LLMs with Preference Data
Reference 18
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T23:27:40.993552Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4b397e49-6698-4093-8187-41235307d4d4 · outbound
This paper cites Prompt caching in the API.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Prompt caching in the API
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.359698Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6d3d14a4-c924-4bcf-88b3-4f48dae1e55c · outbound
This paper cites Vicky Zhao, Lili Qiu, and Dongmei Zhang.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Vicky Zhao, Lili Qiu, and Dongmei Zhang
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.367377Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3003816e-9886-43ac-94ee-e4ddd2fce904 · outbound
This paper cites Qwen2.5 Technical Report.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Qwen2.5 Technical Report
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T10:26:01.760000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1763e294-50f1-4fcd-86ab-444a0b459e82 · outbound
This paper cites Sentence-BERT: Sentence embeddings using siamese BERT- networks.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Sentence-BERT: Sentence embeddings using siamese BERT- networks
Reference 22
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-17T23:22:14.339772Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0da7e975-147b-42f8-8a0e-deaa309cb627 · outbound
This paper cites Efficient Guided Generation for Large Language Models.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Efficient Guided Generation for Large Language Models
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T15:07:13.961671Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0120b1c7-6ea1-478a-bf51-182ebc17cbdb · outbound
This paper cites Xing, Hao Zhang, Joseph E.
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads Xing, Hao Zhang, Joseph E
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:22:14.346565Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
Observation 5a5b3af6-60d5-48f3-8d56-c485a1573f83 · inbound
Compression, structure, and executor capability: a controlled real-cost decomposition of language-model agent skill optimisation cites this paper.
Compression, structure, and executor capability: a controlled real-cost decomposition of language-model agent skill optimisation Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T05:14:41.315225Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.