{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YZTKFAGVUQ5QF57PMT55EO5PB3","short_pith_number":"pith:YZTKFAGV","schema_version":"1.0","canonical_sha256":"c666a280d5a43b02f7ef64fbd23baf0ee51aea4eccf302aab734ff8d86b1d7b4","source":{"kind":"arxiv","id":"2312.05772","version":5},"attestation_state":"computed","paper":{"title":"A^3-CodGen: A Repository-Level Code Generation Framework for Code Reuse with Local-Aware, Global-Aware, and Third-Party-Library-Aware","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dianshu Liao, Huan Jin, Qing Huang, Qinying Li, Shidong Pan, Xiaoxue Ren, Xiaoyu Sun, Zhenchang Xing","submitted_at":"2023-12-10T05:36:06Z","abstract_excerpt":"LLM-based code generation tools are essential to help developers in the software development process. Existing tools often disconnect with the working context, i.e., the code repository, causing the generated code to be not similar to human developers. In this paper, we propose a novel code generation framework, dubbed A^3-CodGen, to harness information within the code repository to generate code with fewer potential logical errors, code redundancy, and library-induced compatibility issues. We identify three types of representative information for the code repository: local-aware information f"},"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":"2312.05772","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-12-10T05:36:06Z","cross_cats_sorted":[],"title_canon_sha256":"25bc2e71c42aeaae03bc6950b36905ca6bb6c82f8822e6fdb0c4a09ca4c1ea3b","abstract_canon_sha256":"aa577dc9c352e222310b40bcb817b50fdc614933ac2694ca4487006b61d7a793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:57.382672Z","signature_b64":"Fkz4+yT06VZAkrMQlwgbrs26skI0VF/NbtBtiZL2S+YkPTFTDGS0fftH+YemdZPRVWjZKcrspqS67EM8VqssCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c666a280d5a43b02f7ef64fbd23baf0ee51aea4eccf302aab734ff8d86b1d7b4","last_reissued_at":"2026-07-05T09:26:57.382171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:57.382171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A^3-CodGen: A Repository-Level Code Generation Framework for Code Reuse with Local-Aware, Global-Aware, and Third-Party-Library-Aware","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dianshu Liao, Huan Jin, Qing Huang, Qinying Li, Shidong Pan, Xiaoxue Ren, Xiaoyu Sun, Zhenchang Xing","submitted_at":"2023-12-10T05:36:06Z","abstract_excerpt":"LLM-based code generation tools are essential to help developers in the software development process. Existing tools often disconnect with the working context, i.e., the code repository, causing the generated code to be not similar to human developers. In this paper, we propose a novel code generation framework, dubbed A^3-CodGen, to harness information within the code repository to generate code with fewer potential logical errors, code redundancy, and library-induced compatibility issues. We identify three types of representative information for the code repository: local-aware information f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05772","kind":"arxiv","version":5},"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/2312.05772/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":"2312.05772","created_at":"2026-07-05T09:26:57.382233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05772v5","created_at":"2026-07-05T09:26:57.382233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05772","created_at":"2026-07-05T09:26:57.382233+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZTKFAGVUQ5Q","created_at":"2026-07-05T09:26:57.382233+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZTKFAGVUQ5QF57P","created_at":"2026-07-05T09:26:57.382233+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZTKFAGV","created_at":"2026-07-05T09:26:57.382233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":224,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3","json":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3.json","graph_json":"https://pith.science/api/pith-number/YZTKFAGVUQ5QF57PMT55EO5PB3/graph.json","events_json":"https://pith.science/api/pith-number/YZTKFAGVUQ5QF57PMT55EO5PB3/events.json","paper":"https://pith.science/paper/YZTKFAGV"},"agent_actions":{"view_html":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3","download_json":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3.json","view_paper":"https://pith.science/paper/YZTKFAGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05772&json=true","fetch_graph":"https://pith.science/api/pith-number/YZTKFAGVUQ5QF57PMT55EO5PB3/graph.json","fetch_events":"https://pith.science/api/pith-number/YZTKFAGVUQ5QF57PMT55EO5PB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3/action/storage_attestation","attest_author":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3/action/author_attestation","sign_citation":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3/action/citation_signature","submit_replication":"https://pith.science/pith/YZTKFAGVUQ5QF57PMT55EO5PB3/action/replication_record"}},"created_at":"2026-07-05T09:26:57.382233+00:00","updated_at":"2026-07-05T09:26:57.382233+00:00"}