{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CPQBBQ7H6CQQNORYCC5C3SFFRL","short_pith_number":"pith:CPQBBQ7H","schema_version":"1.0","canonical_sha256":"13e010c3e7f0a106ba3810ba2dc8a58af9e0caaf613bb5e0caee3bf5192a63e0","source":{"kind":"arxiv","id":"2307.15370","version":1},"attestation_state":"computed","paper":{"title":"Private-Library-Oriented Code Generation with Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bei Chen, Bei Guan, Bingchao Wu, Daoguang Zan, Fengji Zhang, Junzhi Cao, Yilong Yin, Yongji Wang, Yongshun Gong","submitted_at":"2023-07-28T07:43:13Z","abstract_excerpt":"Large language models (LLMs), such as Codex and GPT-4, have recently showcased their remarkable code generation abilities, facilitating a significant boost in coding efficiency. This paper will delve into utilizing LLMs for code generation in private libraries, as they are widely employed in everyday programming. Despite their remarkable capabilities, generating such private APIs poses a formidable conundrum for LLMs, as they inherently lack exposure to these private libraries during pre-training. To address this challenge, we propose a novel framework that emulates the process of programmers "},"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":"2307.15370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-07-28T07:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"6fd37adc4be9046bf1779a9a35b50034264eb8a5784f79d2bf1b3c362e606e1e","abstract_canon_sha256":"03fd4a85b78d32b1229a5dec570074a1f71e13a5b3671a74ba16ff05e9291a9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:34.124964Z","signature_b64":"ugQIN4JeRNraxaxy4DWK4s5VfuOU5p++zHkhcZ/4Enqnhwk4SJUCL612OWCrCMVKXp6PddK60Y5XPX6SbxyiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e010c3e7f0a106ba3810ba2dc8a58af9e0caaf613bb5e0caee3bf5192a63e0","last_reissued_at":"2026-07-05T06:35:34.124554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:34.124554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Private-Library-Oriented Code Generation with Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bei Chen, Bei Guan, Bingchao Wu, Daoguang Zan, Fengji Zhang, Junzhi Cao, Yilong Yin, Yongji Wang, Yongshun Gong","submitted_at":"2023-07-28T07:43:13Z","abstract_excerpt":"Large language models (LLMs), such as Codex and GPT-4, have recently showcased their remarkable code generation abilities, facilitating a significant boost in coding efficiency. This paper will delve into utilizing LLMs for code generation in private libraries, as they are widely employed in everyday programming. Despite their remarkable capabilities, generating such private APIs poses a formidable conundrum for LLMs, as they inherently lack exposure to these private libraries during pre-training. To address this challenge, we propose a novel framework that emulates the process of programmers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15370","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/2307.15370/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":"2307.15370","created_at":"2026-07-05T06:35:34.124611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15370v1","created_at":"2026-07-05T06:35:34.124611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15370","created_at":"2026-07-05T06:35:34.124611+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPQBBQ7H6CQQ","created_at":"2026-07-05T06:35:34.124611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPQBBQ7H6CQQNORY","created_at":"2026-07-05T06:35:34.124611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPQBBQ7H","created_at":"2026-07-05T06:35:34.124611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.17181","citing_title":"A Study of LLMs' Preferences for Libraries and Programming Languages","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22202","citing_title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":222,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL","json":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL.json","graph_json":"https://pith.science/api/pith-number/CPQBBQ7H6CQQNORYCC5C3SFFRL/graph.json","events_json":"https://pith.science/api/pith-number/CPQBBQ7H6CQQNORYCC5C3SFFRL/events.json","paper":"https://pith.science/paper/CPQBBQ7H"},"agent_actions":{"view_html":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL","download_json":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL.json","view_paper":"https://pith.science/paper/CPQBBQ7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15370&json=true","fetch_graph":"https://pith.science/api/pith-number/CPQBBQ7H6CQQNORYCC5C3SFFRL/graph.json","fetch_events":"https://pith.science/api/pith-number/CPQBBQ7H6CQQNORYCC5C3SFFRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL/action/storage_attestation","attest_author":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL/action/author_attestation","sign_citation":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL/action/citation_signature","submit_replication":"https://pith.science/pith/CPQBBQ7H6CQQNORYCC5C3SFFRL/action/replication_record"}},"created_at":"2026-07-05T06:35:34.124611+00:00","updated_at":"2026-07-05T06:35:34.124611+00:00"}