Paper Citation Record · LEDGER

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs

As of 9 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.26571.

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

pith.paper-citation-record.v1
2607.26571 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T13:11:43.364222Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1907ed8a-b135-4683-8189-671584ad812f · outbound

This paper cites Strubell, A.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Strubell, A

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:38.828356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197ccdfc-a6ac-4508-9ddc-17a7131e98a0 · outbound

This paper cites Schwartz, J.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Schwartz, J

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:38.924744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2df4670-7574-4c22-ba9e-c7fa4f3017d7 · outbound

This paper cites Carbon Emissions and Large Neural Network Training.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Carbon Emissions and Large Neural Network Training

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.074788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aba33990-4011-437d-a734-d5a4a069ec81 · outbound

This paper cites Henderson, J.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Henderson, J

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.164934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9875c7d6-8bd2-4588-88a0-c627ef02a8d9 · outbound

This paper cites Quantifying the Carbon Emissions of Machine Learning.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Quantifying the Carbon Emissions of Machine Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.210966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4400b4d-d141-49e6-b735-ad0d2d063303 · outbound

This paper cites Lannelongue, J.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Lannelongue, J

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.354754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 334630c7-b30d-4517-83de-2caea634cdaa · outbound

This paper cites One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.424832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85b24631-cdc6-483d-a483-d074ba1945f3 · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.564911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1c2b3e-e535-4397-9ef7-f56678564854 · outbound

This paper cites Fernandez, C.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Fernandez, C

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.705148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd893533-dcdf-4a32-8ac7-93c4939e9ffb · outbound

This paper cites LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.805738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52743d14-4fb2-4e13-92d6-320c175b7c9d · outbound

This paper cites Vartziotis, M.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Vartziotis, M

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:39.895262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation add9dd61-b892-4869-90fb-00d6de51be54 · outbound

This paper cites Reports average data-center PUE of approximately 1.56.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Reports average data-center PUE of approximately 1.56

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.024977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a513ad35-6fa5-449e-ae28-4253884eed9a · outbound

This paper cites MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.152056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a8e7ab0-9713-42e9-88f2-c3e2ca0d5c2a · outbound

This paper cites nvidia.com/en-us-hopper-architecture/ nvidia-tensor-core-gpu-datasheet, 2023.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs nvidia.com/en-us-hopper-architecture/ nvidia-tensor-core-gpu-datasheet, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.260786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6506491d-b20f-4eae-856a-fceab5c4a22c · outbound

This paper cites Vartziotis, I.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Vartziotis, I

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.363935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7ad372a-b761-4989-a65a-896a26760bbc · outbound

This paper cites Samsi, D.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Samsi, D

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.514887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e20f51e9-3065-4ee1-8bcb-09797508b694 · outbound

This paper cites Luccioni, Y.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Luccioni, Y

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.600504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c7ab08-2b6d-4e65-8274-cb906dcecf31 · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.689889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c185d0-ccf7-48ff-9afe-f0ee325521b6 · outbound

This paper cites Scaling Laws for Neural Language Models.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Scaling Laws for Neural Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.794829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42f4413d-69cb-4d37-ab73-fbdc6a30c809 · outbound

This paper cites Hoffmann, S.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Hoffmann, S

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:40.954963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90810153-35ca-4afe-a854-8f3f428278f6 · outbound

This paper cites Antepara, Z.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Antepara, Z

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.035697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5857ea2-0a83-4617-9cf8-5db570072c7d · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.154612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d16dbe-8ace-4c4a-a30d-29b94ef68e70 · outbound

This paper cites Caravaca, Á.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Caravaca, Á

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.203151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75834720-ff73-482c-b10a-5e5d5fb04a85 · outbound

This paper cites Accessed 2026-05-24.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Accessed 2026-05-24

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.320230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64708f24-b91e-499f-8a7c-b7ff15868b08 · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.413470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4c8f519-e631-421a-a23c-ce3fec318552 · outbound

This paper cites URL: https://docs.nvidia.com/nemo/megatron-bridge/ 0.2.0/models/vlm/ministral3.html.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://docs.nvidia.com/nemo/megatron-bridge/ 0.2.0/models/vlm/ministral3.html

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.535140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29cbfd31-4ff3-489b-8d88-fa3ff096fdea · outbound

This paper cites URL: https: //huggingface.co/google/embeddinggemma-300m.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https: //huggingface.co/google/embeddinggemma-300m

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.627975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd83660b-c961-4e23-9247-470acd859866 · outbound

This paper cites URL: https://www.aimodels.fyi/models/huggingFace/ mxbai-embed-large-v1-mixedbread-ai.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://www.aimodels.fyi/models/huggingFace/ mxbai-embed-large-v1-mixedbread-ai

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.749579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0abd6718-4f77-45bb-8913-ae63f87a1f81 · outbound

This paper cites URL: https: //huggingface.co/Qwen/Qwen3-Embedding-0.6B.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https: //huggingface.co/Qwen/Qwen3-Embedding-0.6B

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.899055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c611f433-a0f3-49f7-b08e-de074612addd · outbound

This paper cites URL: https://huggingface.co/Qwen/Qwen3-32B.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://huggingface.co/Qwen/Qwen3-32B

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.998395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1f3690a-6290-484f-9e45-f52d28749295 · outbound

This paper cites URL: https:// huggingface.co/ibm-granite/granite-3.3-8b-instruct.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https:// huggingface.co/ibm-granite/granite-3.3-8b-instruct

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.147807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13eefec9-a006-43a0-9fe3-4fe3ba361997 · outbound

This paper cites URL: https:// huggingface.co/ibm-granite/granite-3.2-2b-instruct.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https:// huggingface.co/ibm-granite/granite-3.2-2b-instruct

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.294830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d21beee9-bde2-4d05-9438-2c09b65e231b · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.385085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 851a956d-451b-49cb-a4dd-f9194ae61333 · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.555818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58697c33-284c-492a-9402-a404ba9429ba · outbound

This paper cites URL: https://huggingface.co/Qwen/Qwen3-8B.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://huggingface.co/Qwen/Qwen3-8B

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.785940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8cf3cf-2cfe-4af6-9f8d-bffbba19dc22 · outbound

This paper cites URL: https://huggingface.co/Qwen/Qwen3-32B.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://huggingface.co/Qwen/Qwen3-32B

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.867234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d98102-9a6c-4a4e-8e6d-d8d2a6e68bd5 · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.643335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e3b8514-5978-43c3-80ba-af06a6eddc06 · outbound

This paper cites Qwen2.5-Coder Technical Report.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Qwen2.5-Coder Technical Report

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:43.062241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 401bbd6a-2d35-49e3-9b49-13ccf0c252c6 · outbound

This paper cites URL: https:// unsloth.ai/blog/llama3-3.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https:// unsloth.ai/blog/llama3-3

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:43.205902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eacbb8e-01c5-4add-8171-2eb338413db8 · outbound

This paper cites URL: https://huggingface.co/Qwen/Qwen3-1.7B.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://huggingface.co/Qwen/Qwen3-1.7B

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.943502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c671d299-9ea4-44b7-bd9e-06cc18dc67a8 · outbound

This paper cites URL: https://huggingface.co/openai/gpt-oss-20b.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://huggingface.co/openai/gpt-oss-20b

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:43.364222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25c0c2f9-0717-4af6-b3f3-d25d3366c949 · outbound

This paper cites URL: https://huggingface.co/openai/gpt-oss-120b.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs URL: https://huggingface.co/openai/gpt-oss-120b

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:43.276008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13663f69-7b98-4b3d-9601-4f3090f85439 · outbound

This paper cites an unresolved cited work.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:42.484301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02d347e0-d2da-4cfa-83fb-a3a3920c4418 · outbound

This paper cites doi:10.1145/3712285.3759815.

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs doi:10.1145/3712285.3759815

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T13:11:41.096827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.