Paper Citation Record · LEDGER

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications

As of 13 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2607.06411.

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

pith.paper-citation-record.v1
2607.06411 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T08:21:50.175416Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

32 of 32 outbound references displayed

verified exact0
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 25153bba-7766-48ff-8da2-350b24c0482f · outbound

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

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:49.708376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f097b81-7b4e-4618-9fa7-f37081d6ea79 · outbound

This paper cites SWE-Bench+: Enhanced Coding Benchmark for LLMs.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications SWE-Bench+: Enhanced Coding Benchmark for LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:49.775844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20828afc-0fec-467e-9933-0bd1187ff184 · outbound

This paper cites Liang, S.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Liang, S

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:49.976954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2414804-da3f-4c9a-a437-59199db19a10 · outbound

This paper cites Prathifkumar, N.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Prathifkumar, N

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.107696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f5b076-22b7-43ab-a7d4-47a40943f5e4 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.110905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67a67033-2161-4465-93c2-71fcfe096b3f · outbound

This paper cites Badertdinov, A.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Badertdinov, A

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.113607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca14c0ea-849c-4e29-b863-c20cd752f562 · outbound

This paper cites SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.116198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba49c9f0-5eed-44f6-afb9-69243e087812 · outbound

This paper cites Chervyakov, A.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Chervyakov, A

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.119591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb4a7d5-bffc-4c28-9bb3-313c05f67bdb · outbound

This paper cites an unresolved cited work.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.122122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398a7918-8eb2-47f4-bcc1-6394e362bd83 · outbound

This paper cites Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.124329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc6dabd-4f26-488a-8066-685959e86027 · outbound

This paper cites Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.127140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1327ca94-c8d9-4bf7-a999-1f1c80b399dd · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.129688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 448f7704-aa64-4cd9-b2ed-553bc86daad9 · outbound

This paper cites GAIA: a benchmark for General AI Assistants.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications GAIA: a benchmark for General AI Assistants

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.132378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 961877a6-14a1-4ed2-aa27-9d8b3536c034 · outbound

This paper cites MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.134928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 666f9baf-c066-44ac-af9a-50f1e1eb8987 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Evaluating Large Language Models Trained on Code

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.137021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf58742-749a-4db9-b16e-c2eb66ffed38 · outbound

This paper cites Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.139165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b95bbdd-6e60-4b0f-9f58-9c40fb52cc0f · outbound

This paper cites AI Agents That Matter.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications AI Agents That Matter

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.141580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc84386f-7bd2-4ece-b298-087048b31f8a · outbound

This paper cites Kapoor, B.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Kapoor, B

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.143937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 087ac713-6a1f-45db-ba43-78014aef5628 · outbound

This paper cites Measuring AI Ability to Complete Long Software Tasks.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Measuring AI Ability to Complete Long Software Tasks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.145877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58fcc192-7e31-4da4-944f-af8b18859fb3 · outbound

This paper cites RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.147998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc4bb9bc-feab-490c-b45e-35719505f9ec · outbound

This paper cites $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.150187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 220659b0-5cb8-4906-bd48-13c981ac6111 · outbound

This paper cites Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.152279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 036e3ce2-2e83-4ef4-820a-aec381f84720 · outbound

This paper cites ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.154596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3db29c-191f-47ba-8277-1711100b9253 · outbound

This paper cites SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.156961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3877d2cc-b2d2-4b87-acf0-9b9500240cf6 · outbound

This paper cites The Leaderboard Illusion.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications The Leaderboard Illusion

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.159277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fcad652-77e6-4baf-95bc-178d169639c5 · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.161820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9069d21-4c4a-469a-ad8c-0bd1f78a22aa · outbound

This paper cites MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.163874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa951d9d-e589-41f3-9cc1-f482a6729cc1 · outbound

This paper cites Execution-Based Evaluation for Open-Domain Code Generation.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Execution-Based Evaluation for Open-Domain Code Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.166018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b12bbe-234b-4b37-b526-95b20b9c02b4 · outbound

This paper cites HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.168183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e75f657-3fea-452f-a6db-d3c2d022cfea · outbound

This paper cites Если FSM-контекст для апдейта недоступен — сценная обвязка спокойно пропускает апдейт дальше, а не падает.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Если FSM-контекст для апдейта недоступен — сценная обвязка спокойно пропускает апдейт дальше, а не падает

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.171250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7413c14b-3663-49a1-8334-82ff3405278a · outbound

This paper cites Для стратегий FSM, которые и так работают в разрезе чата (CHAT и CHAT_TOPIC), контекст должен определяться и без пользователя — по самому ча- ту/каналу.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Для стратегий FSM, которые и так работают в разрезе чата (CHAT и CHAT_TOPIC), контекст должен определяться и без пользователя — по самому ча- ту/каналу

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.173335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8adc0628-f9d6-4f33-b356-ab6f51a01607 · outbound

This paper cites Существующее поведение для личек и групп ломать нельзя: боты со сценами и без, которые сейчас работают, должны работать ровно как раньше.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications Существующее поведение для личек и групп ломать нельзя: боты со сценами и без, которые сейчас работают, должны работать ровно как раньше

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T08:21:50.175416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.