{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K5ODWVEULPANCEPKPBKSGVI2QE","short_pith_number":"pith:K5ODWVEU","schema_version":"1.0","canonical_sha256":"575c3b54945bc0d111ea785523551a8123e1e3d8a5a42b1432ca5680245c7d90","source":{"kind":"arxiv","id":"2306.03091","version":2},"attestation_state":"computed","paper":{"title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RepoBench introduces a benchmark for repository-level code auto-completion with three tasks covering retrieval, next-line prediction, and combined pipelines in Python and Java.","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Canwen Xu, Julian McAuley, Tianyang Liu","submitted_at":"2023-06-05T17:59:41Z","abstract_excerpt":"Large Language Models (LLMs) have greatly advanced code auto-completion systems, with a potential for substantial productivity enhancements for developers. However, current benchmarks mainly focus on single-file tasks, leaving an assessment gap for more complex, real-world, multi-file programming scenarios. To fill this gap, we introduce RepoBench, a new benchmark specifically designed for evaluating repository-level code auto-completion systems. RepoBench supports both Python and Java and consists of three interconnected evaluation tasks: RepoBench-R (Retrieval), RepoBench-C (Code Completion)"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2306.03091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T17:59:41Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"ceeff49f7ba0aa32aaa1c831c5b85f9963b1d30673b021f87425e0b866202c81","abstract_canon_sha256":"4f978ce0679f6aabc1c24ac4fc16504d52bc907f4a781464e0adb1868eafb631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.936044Z","signature_b64":"NPldJAQqXfwTyOHgdXaMQnITkO3RI5g/xTo0Cq5n26LOf12xCwslVkZw/9rTio0b0Q5ChkShFnF6EQcLSeZeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"575c3b54945bc0d111ea785523551a8123e1e3d8a5a42b1432ca5680245c7d90","last_reissued_at":"2026-05-17T23:38:49.935497Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.935497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RepoBench introduces a benchmark for repository-level code auto-completion with three tasks covering retrieval, next-line prediction, and combined pipelines in Python and Java.","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Canwen Xu, Julian McAuley, Tianyang Liu","submitted_at":"2023-06-05T17:59:41Z","abstract_excerpt":"Large Language Models (LLMs) have greatly advanced code auto-completion systems, with a potential for substantial productivity enhancements for developers. However, current benchmarks mainly focus on single-file tasks, leaving an assessment gap for more complex, real-world, multi-file programming scenarios. To fill this gap, we introduce RepoBench, a new benchmark specifically designed for evaluating repository-level code auto-completion systems. RepoBench supports both Python and Java and consists of three interconnected evaluation tasks: RepoBench-R (Retrieval), RepoBench-C (Code Completion)"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Current benchmarks mainly focus on single-file tasks, leaving an assessment gap for more complex, real-world, multi-file programming scenarios. To fill this gap, we introduce RepoBench.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three constructed tasks and data selection in RepoBench faithfully capture the challenges of real repository-level code completion without introducing selection biases or artificial simplifications.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RepoBench is a new benchmark with retrieval, completion, and pipeline tasks to evaluate code auto-completion systems on entire repositories instead of single files.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RepoBench introduces a benchmark for repository-level code auto-completion with three tasks covering retrieval, next-line prediction, and combined pipelines in Python and Java.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e972ce66cd53486dc9705e68eb3fe3a7309e02a2d3b020bf001d0a4ef0d4432b"},"source":{"id":"2306.03091","kind":"arxiv","version":2},"verdict":{"id":"3dadf7f7-8731-4710-8d51-daec6e67906c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T22:26:46.801004Z","strongest_claim":"Current benchmarks mainly focus on single-file tasks, leaving an assessment gap for more complex, real-world, multi-file programming scenarios. To fill this gap, we introduce RepoBench.","one_line_summary":"RepoBench is a new benchmark with retrieval, completion, and pipeline tasks to evaluate code auto-completion systems on entire repositories instead of single files.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three constructed tasks and data selection in RepoBench faithfully capture the challenges of real repository-level code completion without introducing selection biases or artificial simplifications.","pith_extraction_headline":"RepoBench introduces a benchmark for repository-level code auto-completion with three tasks covering retrieval, next-line prediction, and combined pipelines in Python and Java."},"references":{"count":55,"sample":[{"doi":"","year":2023,"title":"Colt5: Faster long-range transformers with conditional computation, 2023","work_id":"78a986d9-408b-420e-a50a-7edc132af650","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Santacoder: don’t reach for the stars!,","work_id":"5164e1be-7a21-42aa-a4b1-ef335098c626","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Santacoder: don’t reach for the stars! arXiv preprint arXiv:2301.03988","work_id":"bf393c50-a11b-4a0f-8513-52428ede71f7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/msr.2013.6624029","year":2013,"title":"In: 2013 10th Working Conference on Mining Software Repositories (MSR), pp 207--216, doi:10.1109/MSR.2013.6624029","work_id":"5d216e8e-7c15-47d4-b59e-ede90680ea91","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","ref_index":5,"cited_arxiv_id":"2108.07732","is_internal_anchor":true}],"resolved_work":55,"snapshot_sha256":"0f2dc887476a6b7da5163cb2f911da85c091d02251273c1c39cd21ee1bce65e4","internal_anchors":8},"formal_canon":{"evidence_count":1,"snapshot_sha256":"fed04b1cdee6e4ad3748e16db268020938930d0b225749e03aae499d72e323e3"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.03091","created_at":"2026-05-17T23:38:49.935589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03091v2","created_at":"2026-05-17T23:38:49.935589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03091","created_at":"2026-05-17T23:38:49.935589+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5ODWVEULPAN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5ODWVEULPANCEPK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5ODWVEU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":35,"sample":[{"citing_arxiv_id":"2603.03784","citing_title":"Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08686","citing_title":"CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17957","citing_title":"Contextualized Code Pretraining for Code Generation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18561","citing_title":"Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17613","citing_title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08426","citing_title":"KV Cache Offloading for Context-Intensive Tasks","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15315","citing_title":"Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15422","citing_title":"DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.15494","citing_title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2407.11550","citing_title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14018","citing_title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2412.15204","citing_title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2601.13943","citing_title":"RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02605","citing_title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09557","citing_title":"SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2603.06276","citing_title":"Story Point Estimation Using Large Language Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14478","citing_title":"When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":171,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03362","citing_title":"ABTest: Behavior-Driven Testing for AI Coding Agents","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03622","citing_title":"Toward Executable Repository-Level Code Generation via Environment Alignment","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08426","citing_title":"KV Cache Offloading for Context-Intensive Tasks","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2308.14508","citing_title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":226,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28139","citing_title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09059","citing_title":"Evaluating LLM-Generated Code: A Benchmark and Developer Study","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE","json":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE.json","graph_json":"https://pith.science/api/pith-number/K5ODWVEULPANCEPKPBKSGVI2QE/graph.json","events_json":"https://pith.science/api/pith-number/K5ODWVEULPANCEPKPBKSGVI2QE/events.json","paper":"https://pith.science/paper/K5ODWVEU"},"agent_actions":{"view_html":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE","download_json":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE.json","view_paper":"https://pith.science/paper/K5ODWVEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03091&json=true","fetch_graph":"https://pith.science/api/pith-number/K5ODWVEULPANCEPKPBKSGVI2QE/graph.json","fetch_events":"https://pith.science/api/pith-number/K5ODWVEULPANCEPKPBKSGVI2QE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/action/storage_attestation","attest_author":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/action/author_attestation","sign_citation":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/action/citation_signature","submit_replication":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/action/replication_record"}},"created_at":"2026-05-17T23:38:49.935589+00:00","updated_at":"2026-05-17T23:38:49.935589+00:00"}