Paper Citation Record · LEDGER

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software

As of 4 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 3 inbound Pith citation observations for arXiv:2510.15494.

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

pith.paper-citation-record.v1
2510.15494 v2

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T06:39:42.391102Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T09:24:35.760080Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T11:45:45.276547Z

Reference resolution

52 of 52 outbound references displayed

verified exact33
verified fuzzy3
unresolved5
parse uncertain0
malformed identifier2
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5a6c16fb-9df9-4069-8609-34fdc32066e8 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.052000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3b9756af-e638-4a51-a6f3-df53967d064c · outbound

This paper cites Unit testing performance in java projects: Are we there yet?.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unit testing performance in java projects: Are we there yet?

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:41:00.068813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 512aafcd-8ce9-4e71-992d-fd284663d72a · outbound

This paper cites Large Language Models for Mathematical Reasoning: Progresses and Challenges.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Large Language Models for Mathematical Reasoning: Progresses and Challenges

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.361974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0823c032-8cd5-4a69-9ca4-c81cacec1be6 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.074386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 50f41133-da60-48de-a272-00b1cc543d9b · outbound

This paper cites Ando, Chi-Kwong Li, and Roy Mathias.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Ando, Chi-Kwong Li, and Roy Mathias

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T06:41:01.128327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e83462e0-b2ff-49b9-9d2d-e1e9f8132d79 · outbound

This paper cites Program Synthesis with Large Language Models.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Program Synthesis with Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-18T06:41:00.356466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6545bdda-13a0-4a46-8972-3001afbd0766 · outbound

This paper cites author Ralph, P.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software author Ralph, P

Reference 7

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.086108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b2e9d2f1-46a9-42bd-ba32-e236f387661b · outbound

This paper cites RepairAgent: An Autonomous, LLM-Based Agent for Program Repair.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software RepairAgent: An Autonomous, LLM-Based Agent for Program Repair

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:22:16.658570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b186606f-22b7-400a-89ab-2231042e60da · outbound

This paper cites CodeT: Code Generation with Generated Tests.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software CodeT: Code Generation with Generated Tests

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-18T06:41:00.388084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ac13d799-68c0-44a9-bb12-debe19095ec7 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Evaluating Large Language Models Trained on Code

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-18T06:41:00.427565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0c987df0-557a-4f44-83d8-537e92ff10df · outbound

This paper cites Em-assist: Safe automated extractmethod refactoring with llms.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Em-assist: Safe automated extractmethod refactoring with llms

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.062964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 07c2e5ff-674e-4428-8513-92cfda31b967 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 12

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.030923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 882c5a9e-8225-45c2-a318-76369af12fad · outbound

This paper cites CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-18T06:41:00.422172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4284eb6a-437b-4ee3-b008-bc55164ffd3b · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:40:59.950063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 36c273f2-4eb0-4758-874e-9996f7da5d2c · outbound

This paper cites Measuring Coding Challenge Competence With APPS.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Measuring Coding Challenge Competence With APPS

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-18T06:41:00.410903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1b24feb9-2bf9-4ec8-8e1d-c5b418c42646 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-18T06:41:01.117719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation deefe9ae-cfbc-4ea1-bd52-a6a58ca6f7f0 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 17

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.045845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 77edbf0c-32ed-4759-b27f-1b0fcc41b951 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T06:41:00.399248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c695b3c8-d038-4e10-8489-6a67f236b83c · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:40:59.996550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 022f1dc0-3f42-4313-a2b9-901b3bde33d8 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-18T06:41:01.124788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8548075d-0b7d-4161-b5a2-2bc82d8c4df2 · outbound

This paper cites Gall, and Philipp Leitner.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Gall, and Philipp Leitner

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:41:00.352016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2bb1e50b-4daf-4c0e-861a-8d72954175af · outbound

This paper cites Available: https://doi.org/10.1145/3318162.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Available: https://doi.org/10.1145/3318162

Reference 22

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.041538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 03be993f-2a35-495c-972f-e1331f087876 · outbound

This paper cites Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando De Freitas, Koray Kavukcuoglu, and Oriol Vinyals.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando De Freitas, Koray Kavukcuoglu, and Oriol Vinyals

Reference 23

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.003255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3fa271d2-b5df-4cc9-8235-044614fdbf26 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 24

Resolution: verified exact; doi, observed 2026-05-18T06:40:59.955892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fa93ce4b-b593-4e43-b06b-4ba34bc225dc · outbound

This paper cites Evaluating Language Models for Efficient Code Generation.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Evaluating Language Models for Efficient Code Generation

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.443445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ea3a8169-e09d-4381-b92b-320ec3317b18 · outbound

This paper cites RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-18T06:41:00.372262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation db89aecf-4698-42ea-9a5e-493e85395619 · outbound

This paper cites Hellendoorn, Bogdan Vasilescu, and Brad A.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Hellendoorn, Bogdan Vasilescu, and Brad A

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:41:00.367176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0329e519-60bf-4312-bdf0-f0151a694b7e · outbound

This paper cites Reality bites: Assessing the realism of driving scenarios with large language models.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Reality bites: Assessing the realism of driving scenarios with large language models

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:41:00.026649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e61344aa-19ec-4873-be72-4c4c671ad472 · outbound

This paper cites In: International Requirements Engineering Conference.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software In: International Requirements Engineering Conference

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:41:00.019338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d79044e6-4f93-458f-8ea0-f6f28ab7e760 · outbound

This paper cites Lyu, Caiming Xiong, Silvio Savarese, and Doyen Sahoo.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Lyu, Caiming Xiong, Silvio Savarese, and Doyen Sahoo

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:40:59.988140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c7c2f263-d7ca-426e-a8c0-37d39dc2812c · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 32

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.090405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 840256f0-4760-45b5-a3f1-341bca8f12c0 · outbound

This paper cites Rinard , editor =.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Rinard , editor =

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.010391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c293c707-cac1-4ec4-ae8e-dd7aaf8ce2fc · outbound

This paper cites How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.377223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b838ad79-ed1e-41c4-9737-6b024d108a21 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 35

Resolution: malformed identifier; arxiv_id, observed 2026-05-18T06:41:00.438706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b444c224-7003-4d47-903b-c45b91b2e1c7 · outbound

This paper cites Vibe coding: programming through conversation with artificial intelligence.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Vibe coding: programming through conversation with artificial intelligence

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.404987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 313eee01-9698-40d0-b89a-fbb94a32715b · outbound

This paper cites Refactoring.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Refactoring

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:40:59.936624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f0dc0ffe-7d84-45a9-ba49-363596bd46bc · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 38

Resolution: verified exact; doi, observed 2026-05-18T06:40:59.977332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6f56c7c7-1583-4b00-855d-037af3831cbc · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-05-18T06:41:01.110918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9a427976-96cf-4804-b75e-12ab9e768878 · outbound

This paper cites Sánchez, Pedro Delgado-Pérez, Inmaculada Medina-Bulo, and Sergio Segura.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Sánchez, Pedro Delgado-Pérez, Inmaculada Medina-Bulo, and Sergio Segura

Reference 40

Resolution: malformed identifier; doi_truncated, observed 2026-05-18T06:41:00.096459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 373b9b02-c036-450f-b26c-f83a434659f4 · outbound

This paper cites Journal of Educational and Behavioral Statistics25, 101–132 (2000).

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Journal of Educational and Behavioral Statistics25, 101–132 (2000)

Reference 41

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.036550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 89e7c612-1172-4301-a5a7-33b20bf53dc8 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-05-18T06:41:01.114505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0caae76a-04d8-4026-b0c3-213172951dd3 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 43

Resolution: verified exact; doi, observed 2026-05-18T06:40:59.964282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9d9ab323-507f-433b-bd62-792fcb3d9f01 · outbound

This paper cites an unresolved cited work.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-05-18T06:41:01.107928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1bf56378-5518-47c2-850b-4a9b8b9be6d2 · outbound

This paper cites Individual comparisons by ranking methods.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Individual comparisons by ranking methods

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.382559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e66a2b0a-a41d-4767-8453-349cd8e7c8c7 · outbound

This paper cites In 45th IEEE/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14-20.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software In 45th IEEE/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14-20

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:41:00.081512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 976f2dd7-cd3f-470a-a3fd-bf6fcc654bfe · outbound

This paper cites LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.433310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6dbf4672-d2cf-4844-a97f-41f33f25b390 · outbound

This paper cites Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T06:41:01.121852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3b5d9a9f-71f3-4d0f-8b0f-877fe4457145 · outbound

This paper cites InAdvances in Neural Information Processing Systems, A.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software InAdvances in Neural Information Processing Systems, A

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T06:41:01.131414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8a9c1d01-70a9-44d9-bebf-2de9769d0702 · outbound

This paper cites Available: https://doi.org/10.1145/3597503.3623316.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Available: https://doi.org/10.1145/3597503.3623316

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T06:40:59.972046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 66ec87b1-5979-4bb9-b502-f98639268b8b · outbound

This paper cites RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.416630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d1d97fc7-ad59-4126-a863-8e9ed0db2a6e · outbound

This paper cites Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:41:00.347065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c6089825-2d7f-428c-8d11-d7463a8b3648 · outbound

This paper cites Can LLM replace stack overflow? a study on robustness and reliability of large language model code generation.

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software Can LLM replace stack overflow? a study on robustness and reliability of large language model code generation

Reference 53

Resolution: verified exact; doi, observed 2026-05-18T06:41:00.056452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 91a9bead-d72f-4b9d-8cc4-617412170a40 · inbound

CppPerf: An Automated Pipeline and Dataset for Performance-Improving C++ Commits cites this paper.

CppPerf: An Automated Pipeline and Dataset for Performance-Improving C++ Commits Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:56:27.892784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c0433a87-8c1d-449d-8f1c-c9c5c05ed670 · inbound

JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java cites this paper.

JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-01T11:45:45.285527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a9f2dd89-51f3-427a-9787-1da8ffec039b · inbound

JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java cites this paper.

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T09:24:35.760080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.