{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MML2K3OFUDKKI7BRH2YTWZA7DF","short_pith_number":"pith:MML2K3OF","schema_version":"1.0","canonical_sha256":"6317a56dc5a0d4a47c313eb13b641f197d7e6e0e57cfe617457e610504058e5f","source":{"kind":"arxiv","id":"2402.12317","version":2},"attestation_state":"computed","paper":{"title":"EVOR: Evolving Retrieval for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boao Shi, Che Liu, Haoyuan Wu, Hongjin Su, Qian Liu, Shuyang Jiang, Tao Yu, Yuhang Lai","submitted_at":"2024-02-19T17:37:28Z","abstract_excerpt":"Recently the retrieval-augmented generation (RAG) has been successfully applied in code generation. However, existing pipelines for retrieval-augmented code generation (RACG) employ static knowledge bases with a single source, limiting the adaptation capabilities of Large Language Models (LLMs) to domains they have insufficient knowledge of. In this work, we develop a novel pipeline, EVOR, that employs the synchronous evolution of both queries and diverse knowledge bases. On two realistic settings where the external knowledge is required to solve code generation tasks, we compile four new data"},"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":"2402.12317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T17:37:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4f336d2e9ac877f26dd1af198cd63bafb9b7da5439adf5908a45fe9f9184a29","abstract_canon_sha256":"6ca4fd5b9ffecfa4b3d9f93a0c2128d6752544436057b450025a2af6f7bcc4c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:27.409980Z","signature_b64":"C3ohPUzQbwmM6yl43d2E3fQzZXu6ELF+CAByz+f6mn10zWARmyjksuWJctmTxLPELDUgc30pmxpL3s4oIswbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6317a56dc5a0d4a47c313eb13b641f197d7e6e0e57cfe617457e610504058e5f","last_reissued_at":"2026-07-05T09:43:27.409454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:27.409454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVOR: Evolving Retrieval for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boao Shi, Che Liu, Haoyuan Wu, Hongjin Su, Qian Liu, Shuyang Jiang, Tao Yu, Yuhang Lai","submitted_at":"2024-02-19T17:37:28Z","abstract_excerpt":"Recently the retrieval-augmented generation (RAG) has been successfully applied in code generation. However, existing pipelines for retrieval-augmented code generation (RACG) employ static knowledge bases with a single source, limiting the adaptation capabilities of Large Language Models (LLMs) to domains they have insufficient knowledge of. In this work, we develop a novel pipeline, EVOR, that employs the synchronous evolution of both queries and diverse knowledge bases. On two realistic settings where the external knowledge is required to solve code generation tasks, we compile four new data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12317","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/2402.12317/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":"2402.12317","created_at":"2026-07-05T09:43:27.409517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12317v2","created_at":"2026-07-05T09:43:27.409517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12317","created_at":"2026-07-05T09:43:27.409517+00:00"},{"alias_kind":"pith_short_12","alias_value":"MML2K3OFUDKK","created_at":"2026-07-05T09:43:27.409517+00:00"},{"alias_kind":"pith_short_16","alias_value":"MML2K3OFUDKKI7BR","created_at":"2026-07-05T09:43:27.409517+00:00"},{"alias_kind":"pith_short_8","alias_value":"MML2K3OF","created_at":"2026-07-05T09:43:27.409517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17128","citing_title":"Shift-Left High-Level Synthesis Verification via Knowledge-Augmented LLM Agent","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29815","citing_title":"SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22591","citing_title":"Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":228,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08290","citing_title":"Tokalator: A Context Engineering Toolkit for Artificial Intelligence Coding Assistants","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF","json":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF.json","graph_json":"https://pith.science/api/pith-number/MML2K3OFUDKKI7BRH2YTWZA7DF/graph.json","events_json":"https://pith.science/api/pith-number/MML2K3OFUDKKI7BRH2YTWZA7DF/events.json","paper":"https://pith.science/paper/MML2K3OF"},"agent_actions":{"view_html":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF","download_json":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF.json","view_paper":"https://pith.science/paper/MML2K3OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12317&json=true","fetch_graph":"https://pith.science/api/pith-number/MML2K3OFUDKKI7BRH2YTWZA7DF/graph.json","fetch_events":"https://pith.science/api/pith-number/MML2K3OFUDKKI7BRH2YTWZA7DF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF/action/storage_attestation","attest_author":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF/action/author_attestation","sign_citation":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF/action/citation_signature","submit_replication":"https://pith.science/pith/MML2K3OFUDKKI7BRH2YTWZA7DF/action/replication_record"}},"created_at":"2026-07-05T09:43:27.409517+00:00","updated_at":"2026-07-05T09:43:27.409517+00:00"}