{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HJ4ZYRMOYR76WHB5REQCNT4E4I","short_pith_number":"pith:HJ4ZYRMO","schema_version":"1.0","canonical_sha256":"3a799c458ec47feb1c3d892026cf84e23976a151934f7a96144f816b57e181fb","source":{"kind":"arxiv","id":"2504.20799","version":2},"attestation_state":"computed","paper":{"title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dongsun Kim, Jaechang Nam, Jindae Kim, John Youngeun Song, Mijung Kim, Yunseo Lee","submitted_at":"2025-04-29T14:13:57Z","abstract_excerpt":"Recent technical breakthroughs in large language models (LLMs) have enabled them to fluently generate source code. Software developers often leverage both general-purpose and code-specialized LLMs to revise existing code or even generate a whole function from scratch. These capabilities are also beneficial in no-code or low-code contexts, in which one can write programs without a technical background. However, due to their internal design, LLMs are prone to generating hallucinations, which are incorrect, nonsensical, and not justifiable information but difficult to identify its presence. This "},"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":"2504.20799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-29T14:13:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a58e9f78a68b3ec18cc9da12d6df31b16e72ddde331c594c3990360de2876f0c","abstract_canon_sha256":"fd040ace1b10e12420ad97c1b2a4e68e0c01ea91102281297d81072e8276f6ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:23.906563Z","signature_b64":"PoZIT/JNcBd52lTcmYeYGF/qR4eTMg6xdf6J8gdhSYwsbbP8PdqI00OWFaKGpzrZKH7Y3rJ76SqSxqdWEt5hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a799c458ec47feb1c3d892026cf84e23976a151934f7a96144f816b57e181fb","last_reissued_at":"2026-07-05T11:02:23.906086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:23.906086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dongsun Kim, Jaechang Nam, Jindae Kim, John Youngeun Song, Mijung Kim, Yunseo Lee","submitted_at":"2025-04-29T14:13:57Z","abstract_excerpt":"Recent technical breakthroughs in large language models (LLMs) have enabled them to fluently generate source code. Software developers often leverage both general-purpose and code-specialized LLMs to revise existing code or even generate a whole function from scratch. These capabilities are also beneficial in no-code or low-code contexts, in which one can write programs without a technical background. However, due to their internal design, LLMs are prone to generating hallucinations, which are incorrect, nonsensical, and not justifiable information but difficult to identify its presence. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20799","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/2504.20799/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":"2504.20799","created_at":"2026-07-05T11:02:23.906142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20799v2","created_at":"2026-07-05T11:02:23.906142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20799","created_at":"2026-07-05T11:02:23.906142+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJ4ZYRMOYR76","created_at":"2026-07-05T11:02:23.906142+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJ4ZYRMOYR76WHB5","created_at":"2026-07-05T11:02:23.906142+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJ4ZYRMO","created_at":"2026-07-05T11:02:23.906142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25536","citing_title":"A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions","ref_index":58,"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":29,"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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17351","citing_title":"SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I","json":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I.json","graph_json":"https://pith.science/api/pith-number/HJ4ZYRMOYR76WHB5REQCNT4E4I/graph.json","events_json":"https://pith.science/api/pith-number/HJ4ZYRMOYR76WHB5REQCNT4E4I/events.json","paper":"https://pith.science/paper/HJ4ZYRMO"},"agent_actions":{"view_html":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I","download_json":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I.json","view_paper":"https://pith.science/paper/HJ4ZYRMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20799&json=true","fetch_graph":"https://pith.science/api/pith-number/HJ4ZYRMOYR76WHB5REQCNT4E4I/graph.json","fetch_events":"https://pith.science/api/pith-number/HJ4ZYRMOYR76WHB5REQCNT4E4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I/action/storage_attestation","attest_author":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I/action/author_attestation","sign_citation":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I/action/citation_signature","submit_replication":"https://pith.science/pith/HJ4ZYRMOYR76WHB5REQCNT4E4I/action/replication_record"}},"created_at":"2026-07-05T11:02:23.906142+00:00","updated_at":"2026-07-05T11:02:23.906142+00:00"}