Paper Citation Record · LEDGER

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs

As of 20 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 5 inbound Pith citation observations for arXiv:2505.16508.

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

pith.paper-citation-record.v1
2505.16508 v2

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:03:10.285815Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T05:01:16.281918Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T13:26:58.366503Z

Reference resolution

23 of 23 outbound references displayed

verified exact1
verified fuzzy11
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 34ba95dc-8f3e-4aec-bec1-bddc1c205bc4 · outbound

This paper cites Data usage for consumer services faq,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Data usage for consumer services faq,

Reference 1

Resolution: verified exact; raw_fallback, observed 2026-08-07T15:03:10.608413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 065c10a3-5aab-48d4-a43f-97272c48523c · outbound

This paper cites MELTing point: Mobile Evaluation of Language Transformers.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs MELTing point: Mobile Evaluation of Language Transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:08.584216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 991996f3-5e6e-4046-889d-6806864ff512 · outbound

This paper cites LLMCad: Fast and Scalable On-device Large Language Model Inference.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs LLMCad: Fast and Scalable On-device Large Language Model Inference

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:08.669376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 819d60dc-6128-43e6-b98b-a0badecc6103 · outbound

This paper cites Awq: Activation-aware weight quanti- zation for on-device llm compression and acceleration,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Awq: Activation-aware weight quanti- zation for on-device llm compression and acceleration,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:08.729902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ed7b540-95ec-45d4-886e-3e7d95b46fa0 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Llm-pruner: On the structural pruning of large language models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:08.813541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e00be27-8702-415f-9a51-176c459efc07 · outbound

This paper cites Minillm: Knowledge distillation of large language models,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Minillm: Knowledge distillation of large language models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:12.433220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cf1407cc-92d6-4807-9b26-73fbf1a6d025 · outbound

This paper cites Chatgpt: A conversational ai service,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Chatgpt: A conversational ai service,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:12.245715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7da167e2-7954-4c65-a51d-f0c86ea8f921 · outbound

This paper cites Gpt-4o: Enhanced performance across diverse tasks,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Gpt-4o: Enhanced performance across diverse tasks,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:12.092747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation af19a66e-cbae-4148-9fd5-e08a766671e6 · outbound

This paper cites How much energy do llms consume? unveiling the power behind ai,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs How much energy do llms consume? unveiling the power behind ai,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:11.940609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 811cac35-5259-4ab3-9d69-b30f256ab298 · outbound

This paper cites Ai’s growing car- bon footprint,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Ai’s growing car- bon footprint,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:11.644807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fbc22b8a-feb0-461e-9ce6-460bdb0c8a42 · outbound

This paper cites Estimating the carbon footprint of bloom, a 176b parameter language model,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Estimating the carbon footprint of bloom, a 176b parameter language model,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:09.419253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cace8008-afc1-4b05-8e9c-8e7c2d599805 · outbound

This paper cites (2024, Dec.) Incident report: Service down on december 12, 2024.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs (2024, Dec.) Incident report: Service down on december 12, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:11.480181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f1cbc94c-df01-4eff-b49e-4b53270ea68a · outbound

This paper cites Available: https://adasci.org/how-much-energy-do-llms- consume-unveiling-the-power-behind-ai/.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Available: https://adasci.org/how-much-energy-do-llms- consume-unveiling-the-power-behind-ai/

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:11.801102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7e5cda20-09f7-423f-8af0-c749b270af9e · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Gemma 2: Improving Open Language Models at a Practical Size

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:09.539985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dec85007-785b-45b8-804b-2b61ce4ec308 · outbound

This paper cites Small Language Models: Survey, Measurements, and Insights.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Small Language Models: Survey, Measurements, and Insights

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:09.638551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4117fe65-28da-4e27-9e69-399987137da4 · outbound

This paper cites Llama models,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Llama models,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:11.349700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5de477f8-7f82-42e8-b6da-04ed9f54ced7 · outbound

This paper cites Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:09.803169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9936cff-8946-4305-8807-5388ad4298b1 · outbound

This paper cites Finbert: A large language model for extracting information from financial text,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Finbert: A large language model for extracting information from financial text,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:11.162136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 75519e97-be7f-4d58-9048-0720a9d3235f · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Code Llama: Open Foundation Models for Code

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:09.956250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcb9fd31-524a-49a6-bae0-19d1a7488c91 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:10.039916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09c0c1aa-8abb-4d14-9885-aaffde73d969 · outbound

This paper cites BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:10.120350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec11e2e2-5d23-4316-bdbf-33cc8eb3a766 · outbound

This paper cites Rate limits – openai,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Rate limits – openai,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:10.979458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 92a942ef-53ac-4bbb-9107-069815d5abce · outbound

This paper cites Adaptive sliding windows for improved estimation of data center resource utilization,.

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs Adaptive sliding windows for improved estimation of data center resource utilization,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:10.827099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation c66cbdd8-ecab-456e-a4b7-378d932f4f42 · inbound

Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs cites this paper.

Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs Edge-First Language Model Inference: Models, Metrics, and Tradeoffs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T05:01:16.281918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 823794ad-8224-41d0-959a-ca74ffe32ebd · inbound

AI-Enabled Covert Channel Detection in RF Receiver Architectures cites this paper.

AI-Enabled Covert Channel Detection in RF Receiver Architectures Edge-First Language Model Inference: Models, Metrics, and Tradeoffs

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:55:04.047552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4dac0a71-f3a0-4857-953e-fd98b6c9c87e · inbound

BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal cites this paper.

BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal Edge-First Language Model Inference: Models, Metrics, and Tradeoffs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:26:58.368171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9e71d968-f40e-48f0-a08e-a510de7abd32 · inbound

LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters cites this paper.

LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters Edge-First Language Model Inference: Models, Metrics, and Tradeoffs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T18:53:33.574946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb5a434-8b04-48b2-bb97-fe96bb5fd551 · inbound

BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators cites this paper.

BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators Edge-First Language Model Inference: Models, Metrics, and Tradeoffs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T14:28:21.783810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.