Paper Citation Record · LEDGER

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

As of 10 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2505.19481.

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

pith.paper-citation-record.v1
2505.19481 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:16:47.986431Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T08:31:01.469310Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact2
verified fuzzy9
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 84d2d838-09e4-437a-bb71-a379e9e77c1c · outbound

This paper cites Phi-4 Technical Report.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Phi-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:44.685301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ddd0015-a0aa-45d3-930b-5045c122ada8 · outbound

This paper cites Risk and return in high- frequency trading.Journal of Financial and Quantitative Analysis,54993–1024.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Risk and return in high- frequency trading.Journal of Financial and Quantitative Analysis,54993–1024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:50.282112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c98747c-c0a5-448b-aa32-ccfaadd69797 · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:44.824215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a51b0919-7104-4e7b-a15e-6b35930f6708 · outbound

This paper cites E.(1967).

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs E.(1967)

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:50.123459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2109fd91-028e-47fc-acf6-72e90429ab73 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.026717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a04d155-2ff9-4621-967e-c0eac87d9acf · outbound

This paper cites Reinforcement Learning Equilibrium in Limit Order Markets.Journal of Economic Dynamics and Control,144.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Reinforcement Learning Equilibrium in Limit Order Markets.Journal of Economic Dynamics and Control,144

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:49.925155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 061c7b6a-8acf-416f-8cd8-aeb6b27e50cf · outbound

This paper cites KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.310548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef6b394-a704-4f99-9dea-3ab8253335be · outbound

This paper cites TurboAttention: Efficient Attention Approximation For High Throughputs LLMs.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs TurboAttention: Efficient Attention Approximation For High Throughputs LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.426202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 704c6af7-e828-4af3-a14c-e0b581fc656f · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.550536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7784396c-b9d5-4298-b30f-27e412081587 · outbound

This paper cites M.,Uszkoreit, J.,Le, Q.andPetrov, S.(2019).

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs M.,Uszkoreit, J.,Le, Q.andPetrov, S.(2019)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:49.780697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation db4c5c80-bcd4-4458-8166-3f2475342433 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.756234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb75c14-1379-48bc-bb2b-e1624725b7a9 · outbound

This paper cites OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.817948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf0183ab-eb04-4312-9e9d-257fab5dba5a · outbound

This paper cites Camel: Communicative agents for" mind" exploration of large language model society.Advances in Neural Information Processing Systems,3651991–52008.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Camel: Communicative agents for" mind" exploration of large language model society.Advances in Neural Information Processing Systems,3651991–52008

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:49.582197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cdabc844-48c4-4402-99c3-b3fd05469cb3 · outbound

This paper cites Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.018741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 770390de-bbde-42c8-987f-66949810bf77 · outbound

This paper cites QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.099993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dba7ae56-c724-417d-b318-3223159b3d4a · outbound

This paper cites Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.176908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f7cd50-d972-48c5-a496-4a51452519dc · outbound

This paper cites Pointer sentinel mixture models.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Pointer sentinel mixture models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:49.407735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b98d44a7-93d2-4a11-9e1c-b97f5cae9958 · outbound

This paper cites FP8 Formats for Deep Learning.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs FP8 Formats for Deep Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.324314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c873734-c063-4d01-b4e4-58e9d511d51c · outbound

This paper cites DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:16:48.580691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c3820474-25b1-4a27-a874-f80bbc3cef51 · outbound

This paper cites A Practical Mixed Precision Algorithm for Post-Training Quantization.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs A Practical Mixed Precision Algorithm for Post-Training Quantization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.449162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d09da9e9-10f6-40ae-9728-7f9ce9385803 · outbound

This paper cites Qwen2.5 Technical Report.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Qwen2.5 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.527711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69770212-85d2-4c43-9cde-adfd7935c680 · outbound

This paper cites The StarCraft Multi-Agent Challenge.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs The StarCraft Multi-Agent Challenge

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.575546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb7d2383-827a-42cf-b567-47861ccc6daf · outbound

This paper cites SCROLLS: Standardized CompaRison Over Long Language Sequences.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs SCROLLS: Standardized CompaRison Over Long Language Sequences

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.664378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21bb93ef-e647-4911-8c7d-282f4508b882 · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:46.781573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bbdd1aa-68d7-42be-bd80-cb373336e275 · outbound

This paper cites M.(2010).

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs M.(2010)

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:49.255214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e0c4bd7e-11da-4a31-8a9d-3046f10ecb7f · outbound

This paper cites Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:16:48.351117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0f9e06fa-926e-432a-b86a-4d2bedd47ee3 · outbound

This paper cites Gemma 3 Technical Report.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Gemma 3 Technical Report

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.031138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36b0b688-e51f-4466-842c-d5b6b85c391b · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.052422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c57875b-06e5-4221-8c4f-c999c258cb9a · outbound

This paper cites J.,Han, X.,Fu, X.,Zhong, T .,Zeng, J.,Song, M.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs J.,Han, X.,Fu, X.,Zhong, T .,Zeng, J.,Song, M

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:49.086346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f25ee928-77ca-4228-97cf-f5bf27d343fc · outbound

This paper cites AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.386502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa336cfe-16eb-4ce2-a618-5c0dbaac1711 · outbound

This paper cites R.andCao, Y .(2023).

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs R.andCao, Y .(2023)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:48.928927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2d2632fa-ff0d-4efb-8bf8-dc3a53a713a8 · outbound

This paper cites FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.619235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e2ce555-b285-4428-a4e5-b1e7c38b7e90 · outbound

This paper cites A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.697800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da10163d-d38c-4102-ba5e-e01fcc73c35f · outbound

This paper cites Atom: Low-bit Quantization for Efficient and Accurate LLM Serving.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.771772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7a3c2d-ba7d-49ac-908b-6ffb0a82c59f · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs SGLang: Efficient Execution of Structured Language Model Programs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.871852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5b4846-3827-4d00-9ba3-99b763f58db1 · outbound

This paper cites BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:47.986431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5fd66efb-c8a1-42e6-9e11-6413dbdd1f35 · inbound

Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents cites this paper.

Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T08:31:01.469310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.