{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YGFGVR3KTMMYFEJ66T3VCJ7W3J","short_pith_number":"pith:YGFGVR3K","schema_version":"1.0","canonical_sha256":"c18a6ac76a9b1982913ef4f75127f6da6c6c0a42120dfed10734a152c976c110","source":{"kind":"arxiv","id":"2505.10402","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Repetition Problems of LLMs in Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Ge Li, Xue Jiang, Yihong Dong, Yuchen Liu, Zhi Jin","submitted_at":"2025-05-15T15:26:32Z","abstract_excerpt":"With the advent of neural language models, the performance of code generation has been significantly boosted. However, the problem of repetitions during the generation process continues to linger. Previous work has primarily focused on content repetition, which is merely a fraction of the broader repetition problem in code generation. A more prevalent and challenging problem is structural repetition. In structural repetition, the repeated code appears in various patterns but possesses a fixed structure, which can be inherently reflected in grammar. In this paper, we formally define structural "},"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":"2505.10402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T15:26:32Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"869b6ff8c778ba56c63666cd5a5eb0855f6788b190b7c860f405491649c7ea0b","abstract_canon_sha256":"aed6a07729743db31f2938bf699adc487babb332cd7c64a97e861aae21641f17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:37.892968Z","signature_b64":"W7WQSqUV026+nvVFz06LCbd/vzmviMxhTy9kiENkxbqhtO3a7nqGVsebXQ64CFOlnL0ST3/O9of634Pt9QCuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c18a6ac76a9b1982913ef4f75127f6da6c6c0a42120dfed10734a152c976c110","last_reissued_at":"2026-07-05T11:03:37.892473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:37.892473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Repetition Problems of LLMs in Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Ge Li, Xue Jiang, Yihong Dong, Yuchen Liu, Zhi Jin","submitted_at":"2025-05-15T15:26:32Z","abstract_excerpt":"With the advent of neural language models, the performance of code generation has been significantly boosted. However, the problem of repetitions during the generation process continues to linger. Previous work has primarily focused on content repetition, which is merely a fraction of the broader repetition problem in code generation. A more prevalent and challenging problem is structural repetition. In structural repetition, the repeated code appears in various patterns but possesses a fixed structure, which can be inherently reflected in grammar. In this paper, we formally define structural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10402","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/2505.10402/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":"2505.10402","created_at":"2026-07-05T11:03:37.892532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10402v1","created_at":"2026-07-05T11:03:37.892532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10402","created_at":"2026-07-05T11:03:37.892532+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGFGVR3KTMMY","created_at":"2026-07-05T11:03:37.892532+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGFGVR3KTMMYFEJ6","created_at":"2026-07-05T11:03:37.892532+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGFGVR3K","created_at":"2026-07-05T11:03:37.892532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11922","citing_title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","ref_index":12,"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":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J","json":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J.json","graph_json":"https://pith.science/api/pith-number/YGFGVR3KTMMYFEJ66T3VCJ7W3J/graph.json","events_json":"https://pith.science/api/pith-number/YGFGVR3KTMMYFEJ66T3VCJ7W3J/events.json","paper":"https://pith.science/paper/YGFGVR3K"},"agent_actions":{"view_html":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J","download_json":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J.json","view_paper":"https://pith.science/paper/YGFGVR3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10402&json=true","fetch_graph":"https://pith.science/api/pith-number/YGFGVR3KTMMYFEJ66T3VCJ7W3J/graph.json","fetch_events":"https://pith.science/api/pith-number/YGFGVR3KTMMYFEJ66T3VCJ7W3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J/action/storage_attestation","attest_author":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J/action/author_attestation","sign_citation":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J/action/citation_signature","submit_replication":"https://pith.science/pith/YGFGVR3KTMMYFEJ66T3VCJ7W3J/action/replication_record"}},"created_at":"2026-07-05T11:03:37.892532+00:00","updated_at":"2026-07-05T11:03:37.892532+00:00"}