{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YIAW73MURB3GXPCIFJRY2V4NMY","short_pith_number":"pith:YIAW73MU","schema_version":"1.0","canonical_sha256":"c2016fed9488766bbc482a638d578d662220a52cde01b39dd9c1d1a9ba69dcc0","source":{"kind":"arxiv","id":"2503.15231","version":1},"attestation_state":"computed","paper":{"title":"When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jialun Cao, Jiasi Shen, Jingyi Chen, Shing-Chi Cheung, Songqiang Chen","submitted_at":"2025-03-19T14:08:47Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has increasingly shown its power in extending large language models' (LLMs') capability beyond their pre-trained knowledge. Existing works have shown that RAG can help with software development tasks such as code generation, code update, and test generation. Yet, the effectiveness of adapting LLMs to fast-evolving or less common API libraries using RAG remains unknown. To bridge this gap, we take an initial step to study this unexplored yet practical setting - when developers code with a less common library, they often refer to its API documentation; likewi"},"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":"2503.15231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-19T14:08:47Z","cross_cats_sorted":[],"title_canon_sha256":"3769ac7e831848dfa52ba9a40438914dc3364b1b84cd235f6a77c4ccc1dde60d","abstract_canon_sha256":"e01e3d2b7dd90122ceacaa6fcd3be320326716341842434ebf51a3b2b64d2eba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:49.017068Z","signature_b64":"MxwDfm4pl6GeeWgLhLKReXm5pJReU83LnCTtUT7Nc61O/N50rMWANAj/VPfzhBVLPNDBGXVyX1b7TS4Ol63gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2016fed9488766bbc482a638d578d662220a52cde01b39dd9c1d1a9ba69dcc0","last_reissued_at":"2026-07-05T10:34:49.016493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:49.016493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jialun Cao, Jiasi Shen, Jingyi Chen, Shing-Chi Cheung, Songqiang Chen","submitted_at":"2025-03-19T14:08:47Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has increasingly shown its power in extending large language models' (LLMs') capability beyond their pre-trained knowledge. Existing works have shown that RAG can help with software development tasks such as code generation, code update, and test generation. Yet, the effectiveness of adapting LLMs to fast-evolving or less common API libraries using RAG remains unknown. To bridge this gap, we take an initial step to study this unexplored yet practical setting - when developers code with a less common library, they often refer to its API documentation; likewi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15231","kind":"arxiv","version":1},"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/2503.15231/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":"2503.15231","created_at":"2026-07-05T10:34:49.016556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15231v1","created_at":"2026-07-05T10:34:49.016556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15231","created_at":"2026-07-05T10:34:49.016556+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIAW73MURB3G","created_at":"2026-07-05T10:34:49.016556+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIAW73MURB3GXPCI","created_at":"2026-07-05T10:34:49.016556+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIAW73MU","created_at":"2026-07-05T10:34:49.016556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23931","citing_title":"BODHI: Precise OS Kernel Specification Inference","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31135","citing_title":"R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03535","citing_title":"Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01698","citing_title":"BIM Information Extraction Through LLM-based Adaptive Exploration","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY","json":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY.json","graph_json":"https://pith.science/api/pith-number/YIAW73MURB3GXPCIFJRY2V4NMY/graph.json","events_json":"https://pith.science/api/pith-number/YIAW73MURB3GXPCIFJRY2V4NMY/events.json","paper":"https://pith.science/paper/YIAW73MU"},"agent_actions":{"view_html":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY","download_json":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY.json","view_paper":"https://pith.science/paper/YIAW73MU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15231&json=true","fetch_graph":"https://pith.science/api/pith-number/YIAW73MURB3GXPCIFJRY2V4NMY/graph.json","fetch_events":"https://pith.science/api/pith-number/YIAW73MURB3GXPCIFJRY2V4NMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY/action/storage_attestation","attest_author":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY/action/author_attestation","sign_citation":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY/action/citation_signature","submit_replication":"https://pith.science/pith/YIAW73MURB3GXPCIFJRY2V4NMY/action/replication_record"}},"created_at":"2026-07-05T10:34:49.016556+00:00","updated_at":"2026-07-05T10:34:49.016556+00:00"}