{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZZKHSLO4DKGMH7D3G4ODTVDAVQ","short_pith_number":"pith:ZZKHSLO4","schema_version":"1.0","canonical_sha256":"ce54792ddc1a8cc3fc7b371c39d460ac2144f23e4581df080bf67ab96168573d","source":{"kind":"arxiv","id":"2409.20550","version":2},"attestation_state":"computed","paper":{"title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Chong Wang, Jiachi Chen, Yanlin Wang, Zibin Zheng, Ziyao Zhang","submitted_at":"2024-09-30T17:51:15Z","abstract_excerpt":"Code generation aims to automatically generate code from input requirements, significantly enhancing development efficiency. Recent large language models (LLMs) based approaches have shown promising results and revolutionized code generation task. Despite the promising performance, LLMs often generate contents with hallucinations, especially for the code generation scenario requiring the handling of complex contextual dependencies in practical development process. Although previous study has analyzed hallucinations in LLM-powered code generation, the study is limited to standalone function gen"},"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":"2409.20550","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-09-30T17:51:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"be84ce31debd96e3ace33372bb8a85b856bacc2566ed87deaad1f0807256b741","abstract_canon_sha256":"ccbceafd330d935dd30a9f56fc96c4d6323e4043c9267c578e092d917e9eb016"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:06.926154Z","signature_b64":"xp2VrH3EqWmpJTiDvXNiQQweRfu2UIyXjrk03bBD8ofxt3kUc5u0R1qCHBDRJ5vFOcoFnIYqYppMiYKgUWVhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce54792ddc1a8cc3fc7b371c39d460ac2144f23e4581df080bf67ab96168573d","last_reissued_at":"2026-07-05T10:02:06.925667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:06.925667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Chong Wang, Jiachi Chen, Yanlin Wang, Zibin Zheng, Ziyao Zhang","submitted_at":"2024-09-30T17:51:15Z","abstract_excerpt":"Code generation aims to automatically generate code from input requirements, significantly enhancing development efficiency. Recent large language models (LLMs) based approaches have shown promising results and revolutionized code generation task. Despite the promising performance, LLMs often generate contents with hallucinations, especially for the code generation scenario requiring the handling of complex contextual dependencies in practical development process. Although previous study has analyzed hallucinations in LLM-powered code generation, the study is limited to standalone function gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20550","kind":"arxiv","version":2},"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/2409.20550/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":"2409.20550","created_at":"2026-07-05T10:02:06.925725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20550v2","created_at":"2026-07-05T10:02:06.925725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20550","created_at":"2026-07-05T10:02:06.925725+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZKHSLO4DKGM","created_at":"2026-07-05T10:02:06.925725+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZKHSLO4DKGMH7D3","created_at":"2026-07-05T10:02:06.925725+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZKHSLO4","created_at":"2026-07-05T10:02:06.925725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25402","citing_title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25402","citing_title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22202","citing_title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17675","citing_title":"Bridging the Gap on AI-Assisted Scientific Software Development Through Transparency and Traceability","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16771","citing_title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","ref_index":72,"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":153,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ","json":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ.json","graph_json":"https://pith.science/api/pith-number/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/graph.json","events_json":"https://pith.science/api/pith-number/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/events.json","paper":"https://pith.science/paper/ZZKHSLO4"},"agent_actions":{"view_html":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ","download_json":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ.json","view_paper":"https://pith.science/paper/ZZKHSLO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20550&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZZKHSLO4DKGMH7D3G4ODTVDAVQ/action/replication_record"}},"created_at":"2026-07-05T10:02:06.925725+00:00","updated_at":"2026-07-05T10:02:06.925725+00:00"}