Paper Citation Record · LEDGER

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse

As of 15 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 2 inbound Pith citation observations for arXiv:2505.21889.

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

pith.paper-citation-record.v1
2505.21889 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:27:56.457882Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T11:44:03.236830Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-27T05:30:35.738281Z

Reference resolution

39 of 39 outbound references displayed

verified exact1
verified fuzzy21
unresolved16
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1d3518b2-f3de-4c51-b449-572050a9be17 · outbound

This paper cites Neutrino Production via $e^-e^+$ Collision at $Z$-boson Peak.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Neutrino Production via $e^-e^+$ Collision at $Z$-boson Peak

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:53.010377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be474d2-7754-4d82-b44b-fd6b901947d5 · outbound

This paper cites Efficient Training of Language Models to Fill in the Middle.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Efficient Training of Language Models to Fill in the Middle

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:53.164642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 036ffae1-c181-44f3-88d6-c7e06635644e · outbound

This paper cites In: NeurIPS (2020).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NeurIPS (2020)

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.377248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e22ccac4-ec34-4819-bc10-47558a1f6d66 · outbound

This paper cites https://openai.com/index/introducing-canvas/.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse https://openai.com/index/introducing-canvas/

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.176072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ec06ab93-e5d2-4110-a7cb-b53ad00cab5f · outbound

This paper cites arXiv (2021).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse arXiv (2021)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.051758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3fd129b3-58b7-4ad9-9bc3-f8b7179247d7 · outbound

This paper cites an unresolved cited work.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:28:00.902359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e53978e4-30d2-4152-bfb6-71c66c7405c3 · outbound

This paper cites https://docs.aws.amazon.com/codewhisperer/.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse https://docs.aws.amazon.com/codewhisperer/

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.706112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ed596d71-7fcb-4daa-8bff-305148206cc9 · outbound

This paper cites https://github.com/features/copilot.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse https://github.com/features/copilot

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.576109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e767bcbe-d177-4005-85fc-a8e429fed6fb · outbound

This paper cites In: ICLR (2024).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: ICLR (2024)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.391765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ae6318fc-5dc8-4b7e-a5cc-1e57ef433dbe · outbound

This paper cites In: NeurIPS (2022).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NeurIPS (2022)

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.232675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1e7d32a3-1bcb-4410-baa4-d8645e614403 · outbound

This paper cites DeepSeek-V3 Technical Report.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse DeepSeek-V3 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:54.413540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b70f913-49a4-4873-b874-ea47ad437310 · outbound

This paper cites https://zhuanlan.zhihu.com/p/27181462601.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse https://zhuanlan.zhihu.com/p/27181462601

Reference 13

Resolution: verified exact; raw_fallback, observed 2026-08-07T13:27:57.403193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a9319a61-149b-478f-8f50-1bfc4dbcfc77 · outbound

This paper cites In: NAACL-HLT (2019).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NAACL-HLT (2019)

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:54.750554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a133d8cc-d63c-4be4-b235-84a472b9ed53 · outbound

This paper cites In: NeurIPS (2023).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NeurIPS (2023)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.102489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e7f4834e-dff6-473e-8c89-145bd0256be7 · outbound

This paper cites The Llama 3 Herd of Models.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse The Llama 3 Herd of Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:54.959612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3799a13-7087-4f19-b0e7-e71cc8112f23 · outbound

This paper cites In: ICLR (2023).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: ICLR (2023)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.903384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 42ebb158-7328-4c7e-83db-378b1ccdb5ad · outbound

This paper cites In: ATC (2024).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: ATC (2024)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.712255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 84e70d16-b83c-42c8-8bb9-5ea95ee67b32 · outbound

This paper cites In: MLSys (2024) 14 T.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: MLSys (2024) 14 T

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.595273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3ae1345a-91a2-46b2-b409-93bfddcb5089 · outbound

This paper cites DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.385828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca685629-9f3b-454a-978a-d03bf5b02214 · outbound

This paper cites Qwen2.5-Coder Technical Report.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Qwen2.5-Coder Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.430889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd72d76b-b544-46c5-8972-1e804e925ae7 · outbound

This paper cites In: SOSP (2023).https://doi.org/10.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: SOSP (2023).https://doi.org/10

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.478205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b535eaf6-61e6-46e9-84f5-af7ad659db77 · outbound

This paper cites In: OSDI (2024).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: OSDI (2024)

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.427254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 451d4046-99ae-400e-8663-4ea5eb695989 · outbound

This paper cites an unresolved cited work.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:27:59.224584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3de80296-29a0-4bb3-aa16-87cc8db135f2 · outbound

This paper cites https://huggingface.co/meta-llama/Llama-3.1-8B.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse https://huggingface.co/meta-llama/Llama-3.1-8B

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.077716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5595af3d-3ab6-422a-af76-ab9ee48e3a88 · outbound

This paper cites StarCoder 2 and The Stack v2: The Next Generation.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse StarCoder 2 and The Stack v2: The Next Generation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.789896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f006770e-c09a-462f-8dac-c82957f11475 · outbound

This paper cites CodeGen2: Lessons for Training LLMs on Programming and Natural Languages.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.849826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff3889c5-0509-4dea-9757-533fde14364c · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Gemini: A Family of Highly Capable Multimodal Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.891152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05d44a3-bcef-4a32-b21c-ca0a32054a43 · outbound

This paper cites In: MLSys (2023).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: MLSys (2023)

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.884425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 66f1ad18-700b-4c07-b8c9-7ae1e3899799 · outbound

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

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse Code Llama: Open Foundation Models for Code

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:55.968329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 042ed788-7b13-4d0b-ab82-a4010350feab · outbound

This paper cites https://huggingface.co/datasets/bigcode/starcoderdata.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse https://huggingface.co/datasets/bigcode/starcoderdata

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.719117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 77d370ed-ff3c-4e97-948e-fa0ba9f337f0 · outbound

This paper cites In: NeurIPS (2017).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NeurIPS (2017)

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.444500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 19e3c019-f610-4c4f-84be-6bafee6a3e80 · outbound

This paper cites In: ICLR (2024).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: ICLR (2024)

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.252541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d6b1d7ec-990d-4aec-99b0-511948d95c2b · outbound

This paper cites In: EuroSys (2023).https://doi.org/10.1145/ 3552326.3587438.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: EuroSys (2023).https://doi.org/10.1145/ 3552326.3587438

Reference 34

Resolution: malformed identifier; no resolver link, observed 2026-08-07T13:27:56.192156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20485f11-f0ff-4384-aec1-f1de2e68315c · outbound

This paper cites In: ICLR (2024).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: ICLR (2024)

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.107313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 319db48f-fd0e-49a7-ab39-85a9768e9bb7 · outbound

This paper cites In: ACL (2024).https://doi.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: ACL (2024).https://doi

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:56.290558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5daa932f-5fe9-443d-9dc2-569e04448b27 · outbound

This paper cites In: OSDI (2022).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: OSDI (2022)

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.903960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a8a61d9d-9fe0-49fa-8cb2-0a180a22a98c · outbound

This paper cites In: EuroSys (2025).https://doi.org/10.1145/3689031.3696086.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: EuroSys (2025).https://doi.org/10.1145/3689031.3696086

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:56.375333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d05e9b3-5814-4adb-b4c8-62a0a20ff9a9 · outbound

This paper cites In: NeurIPS (2023).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NeurIPS (2023)

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.713222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 39b510c3-7171-4a7d-a157-de4b6961144f · outbound

This paper cites In: NeurIPS (2024).

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse In: NeurIPS (2024)

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.568720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 4b525eff-5756-4369-886d-d32e2d596363 · inbound

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents cites this paper.

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-27T05:30:35.740148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 23eeb072-e8e1-4b93-ac91-1b3f10b351a8 · inbound

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents cites this paper.

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T11:44:03.236830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.