Paper Citation Record · LEDGER

Disproving Program Equivalence with LLMs

As of 12 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2502.18473.

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

pith.paper-citation-record.v1
2502.18473 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T05:54:17.861186Z

measured 20 of 20 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T19:45:34.338092Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

19 of 19 outbound references displayed

verified exact1
verified fuzzy8
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a60a836c-9f6b-45d8-a15f-749b4247e61e · outbound

This paper cites Automated unit test improvement using large language models at M eta.

Disproving Program Equivalence with LLMs Automated unit test improvement using large language models at M eta

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.105514Z

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 9948a37f-d826-4b94-b4fe-3937186e3c16 · outbound

This paper cites CodeT: Code Generation with Generated Tests.

Disproving Program Equivalence with LLMs CodeT: Code Generation with Generated Tests

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.795544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3074b179-cd43-42c5-aaa0-de9d0299692e · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Disproving Program Equivalence with LLMs Evaluating Large Language Models Trained on Code

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.799348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7550de0f-eae8-4dde-9d62-c0284217b314 · outbound

This paper cites Universal Self-Consistency for Large Language Model Generation.

Disproving Program Equivalence with LLMs Universal Self-Consistency for Large Language Model Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.803254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f19c978a-e492-446c-bace-d01fe1e58f6c · outbound

This paper cites Teaching Large Language Models to Self-Debug.

Disproving Program Equivalence with LLMs Teaching Large Language Models to Self-Debug

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.808996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57993b9c-9aec-4d5a-b4cb-5084f327ae06 · outbound

This paper cites Automated testing of refactoring engines.

Disproving Program Equivalence with LLMs Automated testing of refactoring engines

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.093908Z

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 66f442b8-373a-4504-9292-1a66a89bfd07 · outbound

This paper cites SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning.

Disproving Program Equivalence with LLMs SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.816673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8585ea0-7c3c-4c6a-ab67-6de2df08abea · outbound

This paper cites Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?.

Disproving Program Equivalence with LLMs Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.820677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce956eb-9b39-49a3-82c4-f5d1e9c5d5a2 · outbound

This paper cites and Bishop, M.

Disproving Program Equivalence with LLMs and Bishop, M

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.082704Z

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 e759eb1e-9ffe-415a-b295-11203c7957f3 · outbound

This paper cites ChangeGuard: Validating Code Changes via Pairwise Learning-Guided Execution.

Disproving Program Equivalence with LLMs ChangeGuard: Validating Code Changes via Pairwise Learning-Guided Execution

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-09T05:54:17.922488Z

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 6916095f-6a28-4427-bd0c-bbea6779177c · outbound

This paper cites Self-supervised learning to prove equivalence between straight-line programs via rewrite rules.

Disproving Program Equivalence with LLMs Self-supervised learning to prove equivalence between straight-line programs via rewrite rules

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.071092Z

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 ebaa91f4-2df0-46f8-85e1-5ed89425a599 · outbound

This paper cites Compiler validation via equivalence modulo inputs.

Disproving Program Equivalence with LLMs Compiler validation via equivalence modulo inputs

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.058832Z

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 f4f586be-af10-4f90-a88d-03924d136ac5 · outbound

This paper cites P., Lahiri, S.

Disproving Program Equivalence with LLMs P., Lahiri, S

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.048023Z

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 1307cb70-c637-4db1-bc84-0ca6e6045bf2 · outbound

This paper cites S., Wang, Y., and Zhang, L.

Disproving Program Equivalence with LLMs S., Wang, Y., and Zhang, L

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.037283Z

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 e008c9ec-d0dd-42a5-b23d-e94421bec760 · outbound

This paper cites On Leakage of Code Generation Evaluation Datasets.

Disproving Program Equivalence with LLMs On Leakage of Code Generation Evaluation Datasets

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.846372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30f4f378-8d72-497d-8669-895e95d57930 · outbound

This paper cites User interaction models for disambiguation in programming by example.

Disproving Program Equivalence with LLMs User interaction models for disambiguation in programming by example

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T05:54:18.027178Z

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 2595e9de-c4ec-4a1e-bf81-784122c6127c · outbound

This paper cites an unresolved cited work.

Disproving Program Equivalence with LLMs Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-09T05:54:18.015326Z

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 3a77ba75-7c70-4189-9b3f-21a534de5227 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Disproving Program Equivalence with LLMs Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.857319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cbcfe10-2de1-4f59-8ab0-29ba1875fc34 · outbound

This paper cites write newline.

Disproving Program Equivalence with LLMs write newline

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T05:54:17.861186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 42bc0641-7f62-491c-bc91-cc70d2faa0d8 · inbound

How Robustly do LLMs Understand Execution Semantics? cites this paper.

How Robustly do LLMs Understand Execution Semantics? Disproving Program Equivalence with LLMs

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:46:32.914616Z

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.