{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7SMXK362QQX2QKVR7MK37BHDTN","short_pith_number":"pith:7SMXK362","schema_version":"1.0","canonical_sha256":"fc99756fda842fa82ab1fb15bf84e39b53b5261383fb58f84ee4f231afd1c2c6","source":{"kind":"arxiv","id":"2303.17780","version":3},"attestation_state":"computed","paper":{"title":"AceCoder: Utilizing Existing Code to Enhance Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ge Li, Jia Li, Yongmin Li, Yunfei Zhao, Zhi Jin","submitted_at":"2023-03-31T02:57:15Z","abstract_excerpt":"Large Language Models (LLMs) have shown great success in code generation. LLMs take as the input a prompt and output the code. A key question is how to make prompts (i.e., Prompting Techniques). Existing prompting techniques are designed for natural language generation and have low accuracy in code generation.\n  In this paper, we propose a new prompting technique named AceCoder. Our motivation is that code generation meets two unique challenges (i.e., requirement understanding and code implementation). AceCoder contains two novel mechanisms (i.e., guided code generation and example retrieval) "},"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":"2303.17780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-31T02:57:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e4f45bb7e80d723612de2e10c57147030253c52abfddd5b6ad8c989d017acea","abstract_canon_sha256":"0e697e2b5775b2f359a288dbaa6893c534183f1ac4431bfc830245b19b448126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:33.857585Z","signature_b64":"I3MugIBquoxGp0y7hFNWoW7YHqiHEXKwoXER3OmIa87pRLQTiO2IcAjTKnk+5CZib+5OKTsEwWm0fi+VsfUOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc99756fda842fa82ab1fb15bf84e39b53b5261383fb58f84ee4f231afd1c2c6","last_reissued_at":"2026-07-05T06:48:33.857131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:33.857131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AceCoder: Utilizing Existing Code to Enhance Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ge Li, Jia Li, Yongmin Li, Yunfei Zhao, Zhi Jin","submitted_at":"2023-03-31T02:57:15Z","abstract_excerpt":"Large Language Models (LLMs) have shown great success in code generation. LLMs take as the input a prompt and output the code. A key question is how to make prompts (i.e., Prompting Techniques). Existing prompting techniques are designed for natural language generation and have low accuracy in code generation.\n  In this paper, we propose a new prompting technique named AceCoder. Our motivation is that code generation meets two unique challenges (i.e., requirement understanding and code implementation). AceCoder contains two novel mechanisms (i.e., guided code generation and example retrieval) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17780","kind":"arxiv","version":3},"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/2303.17780/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":"2303.17780","created_at":"2026-07-05T06:48:33.857182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17780v3","created_at":"2026-07-05T06:48:33.857182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17780","created_at":"2026-07-05T06:48:33.857182+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SMXK362QQX2","created_at":"2026-07-05T06:48:33.857182+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SMXK362QQX2QKVR","created_at":"2026-07-05T06:48:33.857182+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SMXK362","created_at":"2026-07-05T06:48:33.857182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.01535","citing_title":"Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02977","citing_title":"Large Language Model-Based Agents for Software Engineering: A Survey","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN","json":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN.json","graph_json":"https://pith.science/api/pith-number/7SMXK362QQX2QKVR7MK37BHDTN/graph.json","events_json":"https://pith.science/api/pith-number/7SMXK362QQX2QKVR7MK37BHDTN/events.json","paper":"https://pith.science/paper/7SMXK362"},"agent_actions":{"view_html":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN","download_json":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN.json","view_paper":"https://pith.science/paper/7SMXK362","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17780&json=true","fetch_graph":"https://pith.science/api/pith-number/7SMXK362QQX2QKVR7MK37BHDTN/graph.json","fetch_events":"https://pith.science/api/pith-number/7SMXK362QQX2QKVR7MK37BHDTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN/action/storage_attestation","attest_author":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN/action/author_attestation","sign_citation":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN/action/citation_signature","submit_replication":"https://pith.science/pith/7SMXK362QQX2QKVR7MK37BHDTN/action/replication_record"}},"created_at":"2026-07-05T06:48:33.857182+00:00","updated_at":"2026-07-05T06:48:33.857182+00:00"}