{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ME6XSYDWCEBK3ZIPTM5JLPPPDG","short_pith_number":"pith:ME6XSYDW","schema_version":"1.0","canonical_sha256":"613d7960761102ade50f9b3a95bdef19981b6a06e331979d47c2232291745357","source":{"kind":"arxiv","id":"2504.12608","version":1},"attestation_state":"computed","paper":{"title":"Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bingxu An, Fangming Zou, Juntao Li, Mingwei Liu, Qiuyuan Chen, Xin Peng, Xueying Du, Yiling Lou, Ying Wang, Yong Xu, Zhao Wei, Zuoyu Ou","submitted_at":"2025-04-17T03:13:39Z","abstract_excerpt":"Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code repetition, which refers to the model's tendency to generate structurally redundant code, resulting in inefficiencies and reduced readability. To address this, we conduct the first empirical study to investigate the prevalence and nature of repetition across 19 state-of-the-art code LLMs using three widely-used benchmarks. Our study includes both quantitative and qualitative analyses, revealing that repetition is pervas"},"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":"2504.12608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-17T03:13:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"776aa0ccfc116554819ff0bd77881cd85179b69948f0669c0c6dee4b0e35e645","abstract_canon_sha256":"eab1f779703106f560a27eca15be9272e202aa952ba662c615b30c877fc4182b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:19.541598Z","signature_b64":"EeOlLf/9KgbwXo6bq6GB7+UkBL/P2C87AlPnasxj+HiZpJ6OdBDNn5vrgnOkJ9xDYFUm3nRfr7R4Qdw12kyQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"613d7960761102ade50f9b3a95bdef19981b6a06e331979d47c2232291745357","last_reissued_at":"2026-07-05T10:50:19.541052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:19.541052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bingxu An, Fangming Zou, Juntao Li, Mingwei Liu, Qiuyuan Chen, Xin Peng, Xueying Du, Yiling Lou, Ying Wang, Yong Xu, Zhao Wei, Zuoyu Ou","submitted_at":"2025-04-17T03:13:39Z","abstract_excerpt":"Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code repetition, which refers to the model's tendency to generate structurally redundant code, resulting in inefficiencies and reduced readability. To address this, we conduct the first empirical study to investigate the prevalence and nature of repetition across 19 state-of-the-art code LLMs using three widely-used benchmarks. Our study includes both quantitative and qualitative analyses, revealing that repetition is pervas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12608","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/2504.12608/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":"2504.12608","created_at":"2026-07-05T10:50:19.541112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12608v1","created_at":"2026-07-05T10:50:19.541112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12608","created_at":"2026-07-05T10:50:19.541112+00:00"},{"alias_kind":"pith_short_12","alias_value":"ME6XSYDWCEBK","created_at":"2026-07-05T10:50:19.541112+00:00"},{"alias_kind":"pith_short_16","alias_value":"ME6XSYDWCEBK3ZIP","created_at":"2026-07-05T10:50:19.541112+00:00"},{"alias_kind":"pith_short_8","alias_value":"ME6XSYDW","created_at":"2026-07-05T10:50:19.541112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06464","citing_title":"To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06464","citing_title":"To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG","json":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG.json","graph_json":"https://pith.science/api/pith-number/ME6XSYDWCEBK3ZIPTM5JLPPPDG/graph.json","events_json":"https://pith.science/api/pith-number/ME6XSYDWCEBK3ZIPTM5JLPPPDG/events.json","paper":"https://pith.science/paper/ME6XSYDW"},"agent_actions":{"view_html":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG","download_json":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG.json","view_paper":"https://pith.science/paper/ME6XSYDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12608&json=true","fetch_graph":"https://pith.science/api/pith-number/ME6XSYDWCEBK3ZIPTM5JLPPPDG/graph.json","fetch_events":"https://pith.science/api/pith-number/ME6XSYDWCEBK3ZIPTM5JLPPPDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/action/storage_attestation","attest_author":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/action/author_attestation","sign_citation":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/action/citation_signature","submit_replication":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/action/replication_record"}},"created_at":"2026-07-05T10:50:19.541112+00:00","updated_at":"2026-07-05T10:50:19.541112+00:00"}