{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJJX2R2P4QQ7KGH6BTRVQKQOK4","short_pith_number":"pith:YJJX2R2P","schema_version":"1.0","canonical_sha256":"c2537d474fe421f518fe0ce3582a0e5708d2ebb5124b36a879a7290a31c1f9f6","source":{"kind":"arxiv","id":"2406.14497","version":2},"attestation_state":"computed","paper":{"title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Akari Asai, Daniel Fried, Frank F. Xu, Graham Neubig, Xinyan Velocity Yu, Yiqing Xie, Zora Zhiruo Wang","submitted_at":"2024-06-20T16:59:52Z","abstract_excerpt":"While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate generating accurate and functional code. Despite the success of retrieval-augmented generation (RAG) in various text-oriented tasks, its potential for improving code generation remains under-explored. In this work, we conduct a systematic, large-scale analysis by asking: in what scenarios can retrieval benefit code generation models? and what challenges rema"},"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":"2406.14497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-20T16:59:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"31eeada7e2e15ef18a15f61c203d2f721359ac8683696761a1a12526b681c409","abstract_canon_sha256":"5b37d43c1822a257262cab6984539b08505b5cebad8db7a06ab9f10d08d56e47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:37.846294Z","signature_b64":"SK2NH6qDMf9ygsBqOFcNR/LBc3pfMy+JViLXqZAdX5guIcjBQonVB6gORtMZwZyM6ALMw2hbUC7+z0lZO033DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2537d474fe421f518fe0ce3582a0e5708d2ebb5124b36a879a7290a31c1f9f6","last_reissued_at":"2026-07-05T10:20:37.845764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:37.845764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Akari Asai, Daniel Fried, Frank F. Xu, Graham Neubig, Xinyan Velocity Yu, Yiqing Xie, Zora Zhiruo Wang","submitted_at":"2024-06-20T16:59:52Z","abstract_excerpt":"While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate generating accurate and functional code. Despite the success of retrieval-augmented generation (RAG) in various text-oriented tasks, its potential for improving code generation remains under-explored. In this work, we conduct a systematic, large-scale analysis by asking: in what scenarios can retrieval benefit code generation models? and what challenges rema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14497","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/2406.14497/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":"2406.14497","created_at":"2026-07-05T10:20:37.845835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14497v2","created_at":"2026-07-05T10:20:37.845835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14497","created_at":"2026-07-05T10:20:37.845835+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJJX2R2P4QQ7","created_at":"2026-07-05T10:20:37.845835+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJJX2R2P4QQ7KGH6","created_at":"2026-07-05T10:20:37.845835+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJJX2R2P","created_at":"2026-07-05T10:20:37.845835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29372","citing_title":"On the Road to Personalized Code Intelligence: Portraiting and Assisting Developers Based on Their In-IDE Behaviors","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00642","citing_title":"ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01959","citing_title":"SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16771","citing_title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14488","citing_title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4","json":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4.json","graph_json":"https://pith.science/api/pith-number/YJJX2R2P4QQ7KGH6BTRVQKQOK4/graph.json","events_json":"https://pith.science/api/pith-number/YJJX2R2P4QQ7KGH6BTRVQKQOK4/events.json","paper":"https://pith.science/paper/YJJX2R2P"},"agent_actions":{"view_html":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4","download_json":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4.json","view_paper":"https://pith.science/paper/YJJX2R2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14497&json=true","fetch_graph":"https://pith.science/api/pith-number/YJJX2R2P4QQ7KGH6BTRVQKQOK4/graph.json","fetch_events":"https://pith.science/api/pith-number/YJJX2R2P4QQ7KGH6BTRVQKQOK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4/action/storage_attestation","attest_author":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4/action/author_attestation","sign_citation":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4/action/citation_signature","submit_replication":"https://pith.science/pith/YJJX2R2P4QQ7KGH6BTRVQKQOK4/action/replication_record"}},"created_at":"2026-07-05T10:20:37.845835+00:00","updated_at":"2026-07-05T10:20:37.845835+00:00"}