{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KFUWSXFSIZI46JH4HCY4EQXDGG","short_pith_number":"pith:KFUWSXFS","schema_version":"1.0","canonical_sha256":"5169695cb24651cf24fc38b1c242e33186c0e491e26f23a077cd33f4adf7df24","source":{"kind":"arxiv","id":"2505.13073","version":1},"attestation_state":"computed","paper":{"title":"Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dengfeng Liu, Fang Tan, Feng Liu, Huang Liu, Jucai Zhai, Qianjin Yu, Rui Ye, Xiaoguang Jiang, Yongsheng Du, Zhiguo Yang, Ziqun Li","submitted_at":"2025-05-19T13:09:32Z","abstract_excerpt":"Code completion technology based on large language model has significantly improved the development efficiency of programmers. However, in practical applications, there remains a gap between current commonly used code completion evaluation metrics and users' actual perception. To address this issue, we propose two evaluation metrics for code completion tasks--LCP and ROUGE-LCP, from the perspective of probabilistic modeling. Furthermore, to tackle the lack of effective structural semantic modeling and cross-module dependency information in LLMs for repository-level code completion scenarios, w"},"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":"2505.13073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-19T13:09:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9fa16e72a8cc1869a44ab46f783cc4e42ef993795c54175bfb4a61f7a46c2f5","abstract_canon_sha256":"c57dee54c16690cfd5a3fd35a7bde49ad4aabcf69e655b307e4decd5815e9562"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:51.589677Z","signature_b64":"r8t7Xud1XYTFlGXV4rbg0j9p7KzDu2p0fHF8YgOPBs4FIebvv0cKflwWGHcsfaTG+DS1/ac8kWe3FlhRsKSEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5169695cb24651cf24fc38b1c242e33186c0e491e26f23a077cd33f4adf7df24","last_reissued_at":"2026-06-30T02:16:51.588963Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:51.588963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dengfeng Liu, Fang Tan, Feng Liu, Huang Liu, Jucai Zhai, Qianjin Yu, Rui Ye, Xiaoguang Jiang, Yongsheng Du, Zhiguo Yang, Ziqun Li","submitted_at":"2025-05-19T13:09:32Z","abstract_excerpt":"Code completion technology based on large language model has significantly improved the development efficiency of programmers. However, in practical applications, there remains a gap between current commonly used code completion evaluation metrics and users' actual perception. To address this issue, we propose two evaluation metrics for code completion tasks--LCP and ROUGE-LCP, from the perspective of probabilistic modeling. Furthermore, to tackle the lack of effective structural semantic modeling and cross-module dependency information in LLMs for repository-level code completion scenarios, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13073","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/2505.13073/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":"2505.13073","created_at":"2026-06-30T02:16:51.589044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13073v1","created_at":"2026-06-30T02:16:51.589044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13073","created_at":"2026-06-30T02:16:51.589044+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFUWSXFSIZI4","created_at":"2026-06-30T02:16:51.589044+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFUWSXFSIZI46JH4","created_at":"2026-06-30T02:16:51.589044+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFUWSXFS","created_at":"2026-06-30T02:16:51.589044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG","json":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG.json","graph_json":"https://pith.science/api/pith-number/KFUWSXFSIZI46JH4HCY4EQXDGG/graph.json","events_json":"https://pith.science/api/pith-number/KFUWSXFSIZI46JH4HCY4EQXDGG/events.json","paper":"https://pith.science/paper/KFUWSXFS"},"agent_actions":{"view_html":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG","download_json":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG.json","view_paper":"https://pith.science/paper/KFUWSXFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13073&json=true","fetch_graph":"https://pith.science/api/pith-number/KFUWSXFSIZI46JH4HCY4EQXDGG/graph.json","fetch_events":"https://pith.science/api/pith-number/KFUWSXFSIZI46JH4HCY4EQXDGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG/action/storage_attestation","attest_author":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG/action/author_attestation","sign_citation":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG/action/citation_signature","submit_replication":"https://pith.science/pith/KFUWSXFSIZI46JH4HCY4EQXDGG/action/replication_record"}},"created_at":"2026-06-30T02:16:51.589044+00:00","updated_at":"2026-06-30T02:16:51.589044+00:00"}