{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K5ODWVEULPANCEPKPBKSGVI2QE","short_pith_number":"pith:K5ODWVEU","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"},"canonical_sha256":"575c3b54945bc0d111ea785523551a8123e1e3d8a5a42b1432ca5680245c7d90","source":{"kind":"arxiv","id":"2306.03091","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03091","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03091v2","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03091","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"K5ODWVEULPAN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"K5ODWVEULPANCEPK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"K5ODWVEU","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K5ODWVEULPANCEPKPBKSGVI2QE","target":"record","payload":{"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"},"canonical_sha256":"575c3b54945bc0d111ea785523551a8123e1e3d8a5a42b1432ca5680245c7d90","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"},"source_kind":"arxiv","source_id":"2306.03091","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/NWc7rkHbHA8FSz0iEREN9GVMSkdZkR5XbkhdvkVByDBD7ocUGbNkFSw7BkXCY7NfKimtcld+eAn8PKDK1aBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:22:34.177100Z"},"content_sha256":"a3bbd284233fa6a70c6d5d9839646ee7916ce86eb981207dd1d42293be7b954f","schema_version":"1.0","event_id":"sha256:a3bbd284233fa6a70c6d5d9839646ee7916ce86eb981207dd1d42293be7b954f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K5ODWVEULPANCEPKPBKSGVI2QE","target":"graph","payload":{"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"},"verdict_id":"3dadf7f7-8731-4710-8d51-daec6e67906c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sV6l5XCJhjMJ7BDyEbbrDcXyvBESGloCAGq91gW0ZOptTgsPAqy8TCG2RfCNs8ndtZ5+cx7VLEAikq3oBaeKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:22:34.177731Z"},"content_sha256":"1e551aa4c922c2ee3806cd946dcbf057f0df59dc41f8bcae75fc332e3906b286","schema_version":"1.0","event_id":"sha256:1e551aa4c922c2ee3806cd946dcbf057f0df59dc41f8bcae75fc332e3906b286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/bundle.json","state_url":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5ODWVEULPANCEPKPBKSGVI2QE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T07:22:34Z","links":{"resolver":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE","bundle":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/bundle.json","state":"https://pith.science/pith/K5ODWVEULPANCEPKPBKSGVI2QE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5ODWVEULPANCEPKPBKSGVI2QE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K5ODWVEULPANCEPKPBKSGVI2QE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4f978ce0679f6aabc1c24ac4fc16504d52bc907f4a781464e0adb1868eafb631","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T17:59:41Z","title_canon_sha256":"ceeff49f7ba0aa32aaa1c831c5b85f9963b1d30673b021f87425e0b866202c81"},"schema_version":"1.0","source":{"id":"2306.03091","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03091","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03091v2","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03091","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"K5ODWVEULPAN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"K5ODWVEULPANCEPK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"K5ODWVEU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1e551aa4c922c2ee3806cd946dcbf057f0df59dc41f8bcae75fc332e3906b286","target":"graph","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"e972ce66cd53486dc9705e68eb3fe3a7309e02a2d3b020bf001d0a4ef0d4432b"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"fed04b1cdee6e4ad3748e16db268020938930d0b225749e03aae499d72e323e3"},"paper":{"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)","authors_text":"Canwen Xu, Julian McAuley, Tianyang Liu","cross_cats":["cs.AI","cs.SE"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T17:59:41Z","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems"},"references":{"count":55,"internal_anchors":8,"resolved_work":55,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Colt5: Faster long-range transformers with conditional computation, 2023","work_id":"78a986d9-408b-420e-a50a-7edc132af650","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Santacoder: don’t reach for the stars!,","work_id":"5164e1be-7a21-42aa-a4b1-ef335098c626","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Santacoder: don’t reach for the stars! arXiv preprint arXiv:2301.03988","work_id":"bf393c50-a11b-4a0f-8513-52428ede71f7","year":null},{"cited_arxiv_id":"","doi":"10.1109/msr.2013.6624029","is_internal_anchor":false,"ref_index":4,"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","year":2013},{"cited_arxiv_id":"2108.07732","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","year":2021}],"snapshot_sha256":"0f2dc887476a6b7da5163cb2f911da85c091d02251273c1c39cd21ee1bce65e4"},"source":{"id":"2306.03091","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T22:26:46.801004Z","id":"3dadf7f7-8731-4710-8d51-daec6e67906c","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"3dadf7f7-8731-4710-8d51-daec6e67906c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a3bbd284233fa6a70c6d5d9839646ee7916ce86eb981207dd1d42293be7b954f","target":"record","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4f978ce0679f6aabc1c24ac4fc16504d52bc907f4a781464e0adb1868eafb631","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T17:59:41Z","title_canon_sha256":"ceeff49f7ba0aa32aaa1c831c5b85f9963b1d30673b021f87425e0b866202c81"},"schema_version":"1.0","source":{"id":"2306.03091","kind":"arxiv","version":2}},"canonical_sha256":"575c3b54945bc0d111ea785523551a8123e1e3d8a5a42b1432ca5680245c7d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"575c3b54945bc0d111ea785523551a8123e1e3d8a5a42b1432ca5680245c7d90","first_computed_at":"2026-05-17T23:38:49.935497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.935497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NPldJAQqXfwTyOHgdXaMQnITkO3RI5g/xTo0Cq5n26LOf12xCwslVkZw/9rTio0b0Q5ChkShFnF6EQcLSeZeAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.936044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03091","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3bbd284233fa6a70c6d5d9839646ee7916ce86eb981207dd1d42293be7b954f","sha256:1e551aa4c922c2ee3806cd946dcbf057f0df59dc41f8bcae75fc332e3906b286"],"state_sha256":"1046c9dc588962d7a1327bdee1daa9b5b426aa72109045c0e8b8711df138a8d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jJlIvMmTQnFauC4vK40nO1STMX28kmJ47uLcZpnJ0aY49e6kJUDnQ4RK4xrjGYWk5lhBMevMtnf3fgEs1jnqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:22:34.180400Z","bundle_sha256":"cdd4e9178262949b2c926d103fcd6cef03adced478a45e77bd110f4cb9ecaa49"}}