Paper Citation Record · LEDGER

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching

As of 20 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.15516.

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

pith.paper-citation-record.v1
2607.15516 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T23:14:56.217903Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

22 of 22 outbound references displayed

verified exact0
verified fuzzy0
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a0809f22-7d37-49db-bcae-391ce1b28604 · outbound

This paper cites ACM ICAIF ’25 Workshop on LLMs and Generative AI for Finance.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching ACM ICAIF ’25 Workshop on LLMs and Generative AI for Finance

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.266217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19eeaa77-46ec-4283-8dda-3a9df4e977ba · outbound

This paper cites A Unified Approach to Routing and Cascading for LLMs.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching A Unified Approach to Routing and Cascading for LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.415492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e02edf72-1abe-4718-9950-6e60fbc097ef · outbound

This paper cites Auditing Prompt Caching in Language Model APIs.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Auditing Prompt Caching in Language Model APIs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.505885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd748da0-4d6e-40ff-9f9d-b36300ca1cc9 · outbound

This paper cites LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.635607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46dea7f4-22b0-4d06-a52d-df2dee069eef · outbound

This paper cites LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.779144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a4b7d72-aae2-46c4-93b9-407f4c3e6bdf · outbound

This paper cites 500xCompressor: Generalized Prompt Compression for Large Language Models.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching 500xCompressor: Generalized Prompt Compression for Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.032941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dbfb937-72ed-4373-8c73-3dc72786679e · outbound

This paper cites an unresolved cited work.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.091512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c176990-f89c-46d2-a762-9301e750ae2d · outbound

This paper cites Google; 15 authors.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Google; 15 authors

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.190278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a274ccf-32db-45c9-8427-627e218378d6 · outbound

This paper cites Evaluation across OpenAI, Anthropic, Google on DeepResearch Bench.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Evaluation across OpenAI, Anthropic, Google on DeepResearch Bench

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.353824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d43ba17-ac2f-4da1-bcc0-d9bfa014d235 · outbound

This paper cites Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.449411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9066041-dd6e-4d9b-b383-804dfec0f00f · outbound

This paper cites RouteLLM: Learning to Route LLMs with Preference Data.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching RouteLLM: Learning to Route LLMs with Preference Data

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.597409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0601da62-3a69-4f86-925e-e54011795ef7 · outbound

This paper cites Salesforce AI Research + UIUC.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Salesforce AI Research + UIUC

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.772582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a733540b-2c0a-402e-9374-f26b32b22f98 · outbound

This paper cites Accepted ICLR.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Accepted ICLR

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.841987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a8842c-8dd5-4631-8fcf-d1e7c6c76164 · outbound

This paper cites Converts code, documentation, PDFs, and images into a NetworkX knowledge graph with Leiden community detection and LLM-extracted concept edges.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Converts code, documentation, PDFs, and images into a NetworkX knowledge graph with Leiden community detection and LLM-extracted concept edges

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.923546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf0e75c4-ceb1-4ce9-aa4e-8197b8d7d40c · outbound

This paper cites Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan.τ-bench: A benchmark for tool-agent-user interaction in real-world domains.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan.τ-bench: A benchmark for tool-agent-user interaction in real-world domains

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:55.980635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 619f889d-f4dc-42ee-af05-cc6a2eb03f25 · outbound

This paper cites $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:56.055295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb75c710-b8c2-4b17-a3fb-8b8755367b24 · outbound

This paper cites Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:56.115834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2801332b-4c07-439b-bc95-e961a678a4d8 · outbound

This paper cites "" Feed one observed document version.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching "" Feed one observed document version

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:56.217903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 540d357a-8690-43e4-ac86-9461ff7113a7 · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.054486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f1a10d-9790-47e9-a803-8c988cda7288 · outbound

This paper cites LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:53.715023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffe15007-a4c7-4182-82c4-3865fb982245 · outbound

This paper cites NeurIPS 2025 Poster; 83% hit rate on production prompts.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching NeurIPS 2025 Poster; 83% hit rate on production prompts

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:53.875090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f79c36e8-5ca0-49ed-ae22-5db0b9c5880d · outbound

This paper cites Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference.

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:54.909730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.