{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:POIDNBDGS335MAJRTXYKQN6WGU","short_pith_number":"pith:POIDNBDG","schema_version":"1.0","canonical_sha256":"7b9036846696f7d601319df0a837d6351a3a315ebb14f072d5581cd0268c4b01","source":{"kind":"arxiv","id":"2310.11248","version":2},"attestation_state":"computed","paper":{"title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Bing Xiang, Dan Roth, Hantian Ding, Ming Tan, Murali Krishna Ramanathan, Nihal Jain, Parminder Bhatia, Ramesh Nallapati, Wasi Uddin Ahmad, Yangruibo Ding, Zijian Wang","submitted_at":"2023-10-17T13:18:01Z","abstract_excerpt":"Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting falls short of representing the real-world software development scenario where repositories span multiple files with numerous cross-file dependencies, and accessing and understanding cross-file context is often required to complete the code correctly.\n  To fill in this gap, we propose CrossCodeEval, a diverse and multilingual code completion benchmark that neces"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.11248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-17T13:18:01Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"3e49b42ceb28605133d6632c67286d61374cc8fd1867483ce05077fa9db2efe6","abstract_canon_sha256":"1ff2c13651c358cffc2a7a13618d33df59511f699443cb860c46ce16edadb81a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:45.161402Z","signature_b64":"q++GBIuhJN0siaa8uNhEDmrNjVuciELXYjDdLFNS63h6YB8KkLFOENYUoPjvRMCAXotd4joEwl4Jvi5AgDKeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b9036846696f7d601319df0a837d6351a3a315ebb14f072d5581cd0268c4b01","last_reissued_at":"2026-07-05T07:13:45.160897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:45.160897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Bing Xiang, Dan Roth, Hantian Ding, Ming Tan, Murali Krishna Ramanathan, Nihal Jain, Parminder Bhatia, Ramesh Nallapati, Wasi Uddin Ahmad, Yangruibo Ding, Zijian Wang","submitted_at":"2023-10-17T13:18:01Z","abstract_excerpt":"Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting falls short of representing the real-world software development scenario where repositories span multiple files with numerous cross-file dependencies, and accessing and understanding cross-file context is often required to complete the code correctly.\n  To fill in this gap, we propose CrossCodeEval, a diverse and multilingual code completion benchmark that neces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11248","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.11248/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2310.11248","created_at":"2026-07-05T07:13:45.160958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11248v2","created_at":"2026-07-05T07:13:45.160958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11248","created_at":"2026-07-05T07:13:45.160958+00:00"},{"alias_kind":"pith_short_12","alias_value":"POIDNBDGS335","created_at":"2026-07-05T07:13:45.160958+00:00"},{"alias_kind":"pith_short_16","alias_value":"POIDNBDGS335MAJR","created_at":"2026-07-05T07:13:45.160958+00:00"},{"alias_kind":"pith_short_8","alias_value":"POIDNBDG","created_at":"2026-07-05T07:13:45.160958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00041","citing_title":"ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06492","citing_title":"Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27480","citing_title":"BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14478","citing_title":"When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06683","citing_title":"Benchmarking Requirement-to-Architecture Generation with Hybrid Evaluation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04763","citing_title":"How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU","json":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU.json","graph_json":"https://pith.science/api/pith-number/POIDNBDGS335MAJRTXYKQN6WGU/graph.json","events_json":"https://pith.science/api/pith-number/POIDNBDGS335MAJRTXYKQN6WGU/events.json","paper":"https://pith.science/paper/POIDNBDG"},"agent_actions":{"view_html":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU","download_json":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU.json","view_paper":"https://pith.science/paper/POIDNBDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11248&json=true","fetch_graph":"https://pith.science/api/pith-number/POIDNBDGS335MAJRTXYKQN6WGU/graph.json","fetch_events":"https://pith.science/api/pith-number/POIDNBDGS335MAJRTXYKQN6WGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU/action/storage_attestation","attest_author":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU/action/author_attestation","sign_citation":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU/action/citation_signature","submit_replication":"https://pith.science/pith/POIDNBDGS335MAJRTXYKQN6WGU/action/replication_record"}},"created_at":"2026-07-05T07:13:45.160958+00:00","updated_at":"2026-07-05T07:13:45.160958+00:00"}