{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4MRG7IHIKXIEG5EGSW4JLSJ2TQ","short_pith_number":"pith:4MRG7IHI","schema_version":"1.0","canonical_sha256":"e3226fa0e855d043748695b895c93a9c24b853caffa583e61b7976bf22d3c50b","source":{"kind":"arxiv","id":"2406.07003","version":2},"attestation_state":"computed","paper":{"title":"GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ailun Yu, Bo Shen, Daoguang Zan, Haiyan Zhao, Qianxiang Wang, Wei Liu, Wei Zhang, Zhi Jin","submitted_at":"2024-06-11T06:55:32Z","abstract_excerpt":"The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit less satisfactory performance on repository-level completion due to the lack of repository-specific knowledge in these LLMs. To address this problem, we propose GraphCoder, a retrieval-augmented code completion framework that leverages LLMs' general code knowledge and the repository-specific knowledge via a graph-based retrieval-generation process. In particu"},"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":"2406.07003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-11T06:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"302cd4f7d2c714941e98fc507bf7e85ac8320d5ec2e31092c2dbc80f367a3e5b","abstract_canon_sha256":"ce2f1449e3cb7e91a9f07265535897f00e39feecaa3eff6b454c9fb2e0e29490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:26.856029Z","signature_b64":"NvW1yry3RX2+66do3f88wml0XNsWVEgf/XFh+LmftnxM3IExgIdmxFMN1ZwZ4cKoTzkhIa4RToRlSvFdEinjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3226fa0e855d043748695b895c93a9c24b853caffa583e61b7976bf22d3c50b","last_reissued_at":"2026-07-05T09:06:26.855480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:26.855480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ailun Yu, Bo Shen, Daoguang Zan, Haiyan Zhao, Qianxiang Wang, Wei Liu, Wei Zhang, Zhi Jin","submitted_at":"2024-06-11T06:55:32Z","abstract_excerpt":"The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit less satisfactory performance on repository-level completion due to the lack of repository-specific knowledge in these LLMs. To address this problem, we propose GraphCoder, a retrieval-augmented code completion framework that leverages LLMs' general code knowledge and the repository-specific knowledge via a graph-based retrieval-generation process. In particu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07003","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/2406.07003/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":"2406.07003","created_at":"2026-07-05T09:06:26.855544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07003v2","created_at":"2026-07-05T09:06:26.855544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07003","created_at":"2026-07-05T09:06:26.855544+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MRG7IHIKXIE","created_at":"2026-07-05T09:06:26.855544+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MRG7IHIKXIEG5EG","created_at":"2026-07-05T09:06:26.855544+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MRG7IHI","created_at":"2026-07-05T09:06:26.855544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22082","citing_title":"CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16046","citing_title":"XSearch: Explainable Code Search via Concept-to-Code Alignment","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03618","citing_title":"Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14061","citing_title":"LLM Agents Can See Code Repositories","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16046","citing_title":"XSearch: Explainable Code Search via Concept-to-Code Alignment","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17957","citing_title":"Contextualized Code Pretraining for Code Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15226","citing_title":"Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22659","citing_title":"RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices","ref_index":35,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15676","citing_title":"EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":157,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ","json":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ.json","graph_json":"https://pith.science/api/pith-number/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/graph.json","events_json":"https://pith.science/api/pith-number/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/events.json","paper":"https://pith.science/paper/4MRG7IHI"},"agent_actions":{"view_html":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ","download_json":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ.json","view_paper":"https://pith.science/paper/4MRG7IHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07003&json=true","fetch_graph":"https://pith.science/api/pith-number/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/action/storage_attestation","attest_author":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/action/author_attestation","sign_citation":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/action/citation_signature","submit_replication":"https://pith.science/pith/4MRG7IHIKXIEG5EGSW4JLSJ2TQ/action/replication_record"}},"created_at":"2026-07-05T09:06:26.855544+00:00","updated_at":"2026-07-05T09:06:26.855544+00:00"}