{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ME6XSYDWCEBK3ZIPTM5JLPPPDG","short_pith_number":"pith:ME6XSYDW","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"},"canonical_sha256":"613d7960761102ade50f9b3a95bdef19981b6a06e331979d47c2232291745357","source":{"kind":"arxiv","id":"2504.12608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12608","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12608v1","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12608","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"ME6XSYDWCEBK","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"ME6XSYDWCEBK3ZIP","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"ME6XSYDW","created_at":"2026-07-05T10:50:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ME6XSYDWCEBK3ZIPTM5JLPPPDG","target":"record","payload":{"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"},"canonical_sha256":"613d7960761102ade50f9b3a95bdef19981b6a06e331979d47c2232291745357","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"},"source_kind":"arxiv","source_id":"2504.12608","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vlXSZg7FdOZ7+uHStDM+IA8SEfQuELpZDrLVcdDYou+yLUQbq3swvEanGF24FgieRfpjdwJw0Xu5peYc2+dmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:48:17.205231Z"},"content_sha256":"fc3f01c4c5de5d7c6858f1aaf2a98f32911cf9017011874ced81fe3254e93e20","schema_version":"1.0","event_id":"sha256:fc3f01c4c5de5d7c6858f1aaf2a98f32911cf9017011874ced81fe3254e93e20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ME6XSYDWCEBK3ZIPTM5JLPPPDG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"80qwghNsj1Jq8Ys/zAAVjoLBM48wqYc0WvnlYXOdBkuJJm5+IsKOTXORH1EZhVM0dWLVRlw0oqVPXKwC7bxWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:48:17.205872Z"},"content_sha256":"636975bec44b52e01cc274efeaa0c09a25314042e981191c0c6e4a26d1bd37eb","schema_version":"1.0","event_id":"sha256:636975bec44b52e01cc274efeaa0c09a25314042e981191c0c6e4a26d1bd37eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/bundle.json","state_url":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T06:48:17Z","links":{"resolver":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG","bundle":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/bundle.json","state":"https://pith.science/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ME6XSYDWCEBK3ZIPTM5JLPPPDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ME6XSYDWCEBK3ZIPTM5JLPPPDG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eab1f779703106f560a27eca15be9272e202aa952ba662c615b30c877fc4182b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-17T03:13:39Z","title_canon_sha256":"776aa0ccfc116554819ff0bd77881cd85179b69948f0669c0c6dee4b0e35e645"},"schema_version":"1.0","source":{"id":"2504.12608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12608","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12608v1","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12608","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"ME6XSYDWCEBK","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"ME6XSYDWCEBK3ZIP","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"ME6XSYDW","created_at":"2026-07-05T10:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:636975bec44b52e01cc274efeaa0c09a25314042e981191c0c6e4a26d1bd37eb","target":"graph","created_at":"2026-07-05T10:50:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.12608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-17T03:13:39Z","title":"Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12608","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fc3f01c4c5de5d7c6858f1aaf2a98f32911cf9017011874ced81fe3254e93e20","target":"record","created_at":"2026-07-05T10:50:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eab1f779703106f560a27eca15be9272e202aa952ba662c615b30c877fc4182b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-17T03:13:39Z","title_canon_sha256":"776aa0ccfc116554819ff0bd77881cd85179b69948f0669c0c6dee4b0e35e645"},"schema_version":"1.0","source":{"id":"2504.12608","kind":"arxiv","version":1}},"canonical_sha256":"613d7960761102ade50f9b3a95bdef19981b6a06e331979d47c2232291745357","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"613d7960761102ade50f9b3a95bdef19981b6a06e331979d47c2232291745357","first_computed_at":"2026-07-05T10:50:19.541052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:19.541052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EeOlLf/9KgbwXo6bq6GB7+UkBL/P2C87AlPnasxj+HiZpJ6OdBDNn5vrgnOkJ9xDYFUm3nRfr7R4Qdw12kyQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:19.541598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc3f01c4c5de5d7c6858f1aaf2a98f32911cf9017011874ced81fe3254e93e20","sha256:636975bec44b52e01cc274efeaa0c09a25314042e981191c0c6e4a26d1bd37eb"],"state_sha256":"4bf21a29a8ae5c67fa5a1c016dd254bc7846af7cd2c928611d7322d10e57b02b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAPscxmzNA/rt/aM4bofI1LHdQVNOnvf0+B5eDjMp9xWeJ24OjFHnpAvhcLGpaifuVKlLzGVnTrct8Wyv79DDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:48:17.209269Z","bundle_sha256":"7127e83646b550a55456a74663cc49376717ba63fe7462dc15f1b6226cd92d40"}}