Paper Citation Record · LEDGER

Evaluating Agent-based Program Repair at Google

As of 12 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 9 inbound Pith citation observations for arXiv:2501.07531.

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

pith.paper-citation-record.v1
2501.07531 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:42:02.279761Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T23:10:11.075376Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-10T06:15:00.866473Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy20
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9c03eacb-014a-444e-b98e-3236d9572434 · outbound

This paper cites Swe-bench: Can language models resolve real-world github issues?.

Evaluating Agent-based Program Repair at Google Swe-bench: Can language models resolve real-world github issues?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.155157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a54b01-06f4-4142-9966-8378934b4b63 · outbound

This paper cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering.

Evaluating Agent-based Program Repair at Google SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.159739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b624f4f-ad9c-4bd9-8950-c6e8de795020 · outbound

This paper cites Autocoderover: Autonomous program improvement,.

Evaluating Agent-based Program Repair at Google Autocoderover: Autonomous program improvement,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.164065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46d7803d-1ed1-4040-a7bf-c73e91d0ab6b · outbound

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

Evaluating Agent-based Program Repair at Google RepairAgent: An Autonomous, LLM-Based Agent for Program Repair

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.168538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1a913c-3158-445f-b9e1-0b5d2c4360dc · outbound

This paper cites CodeR: Issue Resolving with Multi-Agent and Task Graphs.

Evaluating Agent-based Program Repair at Google CodeR: Issue Resolving with Multi-Agent and Task Graphs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.173125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6745bad5-2dc9-44f9-9dde-0a8306246171 · outbound

This paper cites AutoDev: Automated AI-Driven Development.

Evaluating Agent-based Program Repair at Google AutoDev: Automated AI-Driven Development

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.177254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b6fae6-5ffb-4bfc-beac-60cf5b03598a · outbound

This paper cites OpenHands: An Open Platform for AI Software Developers as Generalist Agents.

Evaluating Agent-based Program Repair at Google OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.181916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3905fe6-dfa5-48ff-afbf-97493e586567 · outbound

This paper cites SpecRover: Code Intent Extraction via LLMs.

Evaluating Agent-based Program Repair at Google SpecRover: Code Intent Extraction via LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.186789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de9cd63a-6765-486f-852d-f535397665aa · outbound

This paper cites MarsCode Agent: AI-native Automated Bug Fixing.

Evaluating Agent-based Program Repair at Google MarsCode Agent: AI-native Automated Bug Fixing

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.191985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46cb393a-783a-41c7-80ac-de6f9443e6ef · outbound

This paper cites Why google stores billions of lines of code in a single repository,.

Evaluating Agent-based Program Repair at Google Why google stores billions of lines of code in a single repository,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.611233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation aaa784f6-ff40-42fc-a00d-d7562db82c29 · outbound

This paper cites Distributed Builds,.

Evaluating Agent-based Program Repair at Google Distributed Builds,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.600962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation de8c7892-7a39-4b90-b1b2-732a3a05f588 · outbound

This paper cites How developers search for code: a case study,.

Evaluating Agent-based Program Repair at Google How developers search for code: a case study,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.590903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 58609087-3a5a-4286-bcfd-355ceb798427 · outbound

This paper cites Harnessing evolution for multi-hunk program repair,.

Evaluating Agent-based Program Repair at Google Harnessing evolution for multi-hunk program repair,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.581034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5845c6cd-69a7-4836-a93a-c3ce512f98b6 · outbound

This paper cites Dissection of a bug dataset: Anatomy of 395 patches from defects4j,.

Evaluating Agent-based Program Repair at Google Dissection of a bug dataset: Anatomy of 395 patches from defects4j,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.570333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2b0aa60b-24db-42e3-9481-09d54793c561 · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

Evaluating Agent-based Program Repair at Google React: Synergizing reasoning and acting in language models,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.559672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f6932b46-9356-4de6-b5b4-c4fcea33249b · outbound

This paper cites Executable code actions elicit better llm agents,.

Evaluating Agent-based Program Repair at Google Executable code actions elicit better llm agents,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.550325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0ab0ded7-81d8-446d-a007-c58840d006af · outbound

This paper cites Building a distributed build system at google scale,.

Evaluating Agent-based Program Repair at Google Building a distributed build system at google scale,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.539964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0e330c07-fcc6-45df-9638-da65930b89fe · outbound

This paper cites Smart build targets batching service at Google,.

Evaluating Agent-based Program Repair at Google Smart build targets batching service at Google,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.529887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 183ce7b4-5eb7-4196-b6f5-29dfc77801cf · outbound

This paper cites An analysis of patch plausibility and correctness for generate-and-validate patch generation systems,.

Evaluating Agent-based Program Repair at Google An analysis of patch plausibility and correctness for generate-and-validate patch generation systems,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.519045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9e34f1cb-49ac-41c3-a8c5-7d4641ef9697 · outbound

This paper cites Identifying patch correctness in test-based program repair,.

Evaluating Agent-based Program Repair at Google Identifying patch correctness in test-based program repair,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.508844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 55b84107-331b-43c5-b3e8-92eb57a6b772 · outbound

This paper cites Exploring the differences between plausible and correct patches at fine-grained level,.

Evaluating Agent-based Program Repair at Google Exploring the differences between plausible and correct patches at fine-grained level,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.498581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f41b2982-de3e-4d89-a48d-48968e508ed6 · outbound

This paper cites On the efficiency of test suite based program repair: A systematic assessment of 16 automated repair systems for java programs,.

Evaluating Agent-based Program Repair at Google On the efficiency of test suite based program repair: A systematic assessment of 16 automated repair systems for java programs,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.487511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 75f984a3-68e8-4d7f-bfee-e36978d3011d · outbound

This paper cites A large-scale empirical review of patch correctness checking approaches,.

Evaluating Agent-based Program Repair at Google A large-scale empirical review of patch correctness checking approaches,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.476755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9ea02761-b901-4aad-87fd-824d93403df3 · outbound

This paper cites Fowler, Refactoring: improving the design of existing code.

Evaluating Agent-based Program Repair at Google Fowler, Refactoring: improving the design of existing code

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.252263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8669f8fe-2171-4d44-99fc-1d61d0a463c4 · outbound

This paper cites Gemini 1.5: Our next-generation model, now available for private preview in google ai studio,.

Evaluating Agent-based Program Repair at Google Gemini 1.5: Our next-generation model, now available for private preview in google ai studio,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.459183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 15400d64-d8da-4703-807b-26225ec7ee33 · outbound

This paper cites Automatic software repair: A bibliography,.

Evaluating Agent-based Program Repair at Google Automatic software repair: A bibliography,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.448119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0f4ee784-d273-4c5f-8b6b-eed3ef08ef80 · outbound

This paper cites Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt,.

Evaluating Agent-based Program Repair at Google Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.261400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb655d37-2c67-4cf4-b8a7-eda0f23e7962 · outbound

This paper cites An empirical study on real bug fixes,.

Evaluating Agent-based Program Repair at Google An empirical study on real bug fixes,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.429526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d8a0cb6f-08ed-41ec-926b-3fca6d57ed3b · outbound

This paper cites Introducing Devin, the first AI software engineer,.

Evaluating Agent-based Program Repair at Google Introducing Devin, the first AI software engineer,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.418316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 891a0477-0706-461a-b094-83b91c52ddc3 · outbound

This paper cites Less training, more repairing please: revisiting automated program repair via zero-shot learning,.

Evaluating Agent-based Program Repair at Google Less training, more repairing please: revisiting automated program repair via zero-shot learning,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.407777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e5037259-0577-437e-8ba9-a0680f6b6686 · outbound

This paper cites Agentless: Demystifying LLM-based Software Engineering Agents.

Evaluating Agent-based Program Repair at Google Agentless: Demystifying LLM-based Software Engineering Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:02.275620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3514d08c-7e23-4ae8-9a7f-d9f69538cd65 · outbound

This paper cites Large language models for test-free fault localization,.

Evaluating Agent-based Program Repair at Google Large language models for test-free fault localization,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:42:02.394744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation e5e67d58-78c2-41d8-bd8e-287a37b64d02 · inbound

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks cites this paper.

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks Evaluating Agent-based Program Repair at Google

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T23:10:11.075376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd6c01a8-7067-4071-a951-b66c888fa0d9 · inbound

NoCode-bench: A Benchmark for Evaluating Natural Language-Driven Feature Addition cites this paper.

NoCode-bench: A Benchmark for Evaluating Natural Language-Driven Feature Addition Evaluating Agent-based Program Repair at Google

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T14:43:14.340240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c81771d0-3c9b-4c31-965b-34c3c6477474 · inbound

Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback cites this paper.

Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback Evaluating Agent-based Program Repair at Google

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T14:37:17.535332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e46f6f-bfac-4f02-ac5b-c13e21404a97 · inbound

Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair cites this paper.

Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair Evaluating Agent-based Program Repair at Google

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T22:21:20.733478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bcc2fe4-120e-4ab1-b47a-0d6c994974bb · inbound

LLM-Based Automated Diagnosis Of Integration Test Failures At Google cites this paper.

LLM-Based Automated Diagnosis Of Integration Test Failures At Google Evaluating Agent-based Program Repair at Google

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:16:05.417442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 26dc6317-d2ed-4156-abfb-ef52eda3b4a1 · inbound

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap cites this paper.

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap Evaluating Agent-based Program Repair at Google

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:00:03.620735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7635cf93-5fa4-498e-aead-7111a7eef714 · inbound

From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements cites this paper.

From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements Evaluating Agent-based Program Repair at Google

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-19T23:22:52.212558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 95ecec71-523b-4f07-818e-8e98be86659b · inbound

Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment cites this paper.

Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment Evaluating Agent-based Program Repair at Google

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-04T18:00:00.845027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dc5f97d5-9bbc-4f93-b50d-95b185e4b222 · inbound

MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs cites this paper.

MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs Evaluating Agent-based Program Repair at Google

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T12:47:01.165754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.