{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YEBXWGUGPDMB7C2QYGDCTWGB7V","short_pith_number":"pith:YEBXWGUG","schema_version":"1.0","canonical_sha256":"c1037b1a8678d81f8b50c18629d8c1fd5a698345d424278c41ec0bb0250edfc4","source":{"kind":"arxiv","id":"2510.04905","version":3},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Yao Qin, Yepang Liu, Yicheng Tao, Yuante Li","submitted_at":"2025-10-06T15:20:03Z","abstract_excerpt":"Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved strong performance at the function and file levels, real-world software engineering requires reasoning over entire repositories, including cross-file dependencies, evolving execution environments, and global semantic consistency. This challenge has led to the emergence of Repository-Level Code Generation (RLCG), where models must retrieve, organize, and utilize repository-scale context to generate coherent and executable code changes. To address these c"},"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":"2510.04905","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-10-06T15:20:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"682525a92a9fd2ee65d94c12f33a46d725bb907dfa2457a340055c662aeb09da","abstract_canon_sha256":"988e0032009cf0e02b5cb3a6956e44f451cf25199ce9a5f4a4b5ac0c55c5a9c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:04:53.034864Z","signature_b64":"Rr8xqwm2EvM1Nyzhj1VtCyy6Z6KIkYEw07evltBewuJ2HKIONFk5pISF0lwN6VJ8iOboGS3TNu8HTY5XiHaTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1037b1a8678d81f8b50c18629d8c1fd5a698345d424278c41ec0bb0250edfc4","last_reissued_at":"2026-05-21T02:04:53.033970Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:04:53.033970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Yao Qin, Yepang Liu, Yicheng Tao, Yuante Li","submitted_at":"2025-10-06T15:20:03Z","abstract_excerpt":"Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved strong performance at the function and file levels, real-world software engineering requires reasoning over entire repositories, including cross-file dependencies, evolving execution environments, and global semantic consistency. This challenge has led to the emergence of Repository-Level Code Generation (RLCG), where models must retrieve, organize, and utilize repository-scale context to generate coherent and executable code changes. To address these c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04905","kind":"arxiv","version":3},"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/2510.04905/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":"2510.04905","created_at":"2026-05-21T02:04:53.034091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.04905v3","created_at":"2026-05-21T02:04:53.034091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04905","created_at":"2026-05-21T02:04:53.034091+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEBXWGUGPDMB","created_at":"2026-05-21T02:04:53.034091+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEBXWGUGPDMB7C2Q","created_at":"2026-05-21T02:04:53.034091+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEBXWGUG","created_at":"2026-05-21T02:04:53.034091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.17965","citing_title":"BLAgent: Agentic RAG for File-Level Bug Localization","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22018","citing_title":"Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25960","citing_title":"Large Language Models for Multilingual Code Intelligence: A Survey","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04894","citing_title":"SynConfRoute: Syntax-Aware Routing for Efficient Code Completion with Small CodeLLMs","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04763","citing_title":"How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06373","citing_title":"Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V","json":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V.json","graph_json":"https://pith.science/api/pith-number/YEBXWGUGPDMB7C2QYGDCTWGB7V/graph.json","events_json":"https://pith.science/api/pith-number/YEBXWGUGPDMB7C2QYGDCTWGB7V/events.json","paper":"https://pith.science/paper/YEBXWGUG"},"agent_actions":{"view_html":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V","download_json":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V.json","view_paper":"https://pith.science/paper/YEBXWGUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.04905&json=true","fetch_graph":"https://pith.science/api/pith-number/YEBXWGUGPDMB7C2QYGDCTWGB7V/graph.json","fetch_events":"https://pith.science/api/pith-number/YEBXWGUGPDMB7C2QYGDCTWGB7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V/action/storage_attestation","attest_author":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V/action/author_attestation","sign_citation":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V/action/citation_signature","submit_replication":"https://pith.science/pith/YEBXWGUGPDMB7C2QYGDCTWGB7V/action/replication_record"}},"created_at":"2026-05-21T02:04:53.034091+00:00","updated_at":"2026-05-21T02:04:53.034091+00:00"}