{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PQURVD7WDMUCXDVVB67Z7K5ZG7","short_pith_number":"pith:PQURVD7W","schema_version":"1.0","canonical_sha256":"7c291a8ff61b282b8eb50fbf9fabb937cd35e825a5a7fd1aa643df0fecc478c1","source":{"kind":"arxiv","id":"2503.06327","version":3},"attestation_state":"computed","paper":{"title":"A Taxonomy of Inefficiencies in LLM-Generated Python Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Altaf Allah Abbassi, Amin Nikanjam, Foutse Khomh, Leuson Da Silva","submitted_at":"2025-03-08T19:51:52Z","abstract_excerpt":"Large Language Models (LLMs) are widely adopted for automated code generation with promising results. Although prior research has assessed LLM-generated code and identified various quality issues -- such as redundancy, poor maintainability, and sub-optimal performance a systematic understanding and categorization of these inefficiencies remain unexplored. Without such knowledge, practitioners struggle to optimize LLM-generated code for real-world applications, limiting its adoption. This study can also guide improving code LLMs, enhancing the quality and efficiency of code generation. Therefor"},"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":"2503.06327","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-08T19:51:52Z","cross_cats_sorted":[],"title_canon_sha256":"40fbaea9ac25879a5b8a6b1bde411ee8ebb1fc7d7beb19bbfa55e9b724c998a7","abstract_canon_sha256":"f04ef9a22f7d2cf484e3e05a2588a4aea56587fca626c4388ba2ece2e7627924"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:23.088594Z","signature_b64":"y2mdgSfx/xHDI9CTxFDfFHcMAMcaztmv6SmL0PviA0oyc7vvsdYh/7Y/P8hZtoTWsOJfjwZXUEb6iokq814KDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c291a8ff61b282b8eb50fbf9fabb937cd35e825a5a7fd1aa643df0fecc478c1","last_reissued_at":"2026-07-05T11:51:23.088094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:23.088094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Taxonomy of Inefficiencies in LLM-Generated Python Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Altaf Allah Abbassi, Amin Nikanjam, Foutse Khomh, Leuson Da Silva","submitted_at":"2025-03-08T19:51:52Z","abstract_excerpt":"Large Language Models (LLMs) are widely adopted for automated code generation with promising results. Although prior research has assessed LLM-generated code and identified various quality issues -- such as redundancy, poor maintainability, and sub-optimal performance a systematic understanding and categorization of these inefficiencies remain unexplored. Without such knowledge, practitioners struggle to optimize LLM-generated code for real-world applications, limiting its adoption. This study can also guide improving code LLMs, enhancing the quality and efficiency of code generation. Therefor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06327","kind":"arxiv","version":3},"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/2503.06327/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":"2503.06327","created_at":"2026-07-05T11:51:23.088151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06327v3","created_at":"2026-07-05T11:51:23.088151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06327","created_at":"2026-07-05T11:51:23.088151+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQURVD7WDMUC","created_at":"2026-07-05T11:51:23.088151+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQURVD7WDMUCXDVV","created_at":"2026-07-05T11:51:23.088151+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQURVD7W","created_at":"2026-07-05T11:51:23.088151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00118","citing_title":"An Empirical Study on Logging Evolution On Stack Overflow: Trends, Topics, and Challenges","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31097","citing_title":"SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19353","citing_title":"Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation","ref_index":1,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02431","citing_title":"ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7","json":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7.json","graph_json":"https://pith.science/api/pith-number/PQURVD7WDMUCXDVVB67Z7K5ZG7/graph.json","events_json":"https://pith.science/api/pith-number/PQURVD7WDMUCXDVVB67Z7K5ZG7/events.json","paper":"https://pith.science/paper/PQURVD7W"},"agent_actions":{"view_html":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7","download_json":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7.json","view_paper":"https://pith.science/paper/PQURVD7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06327&json=true","fetch_graph":"https://pith.science/api/pith-number/PQURVD7WDMUCXDVVB67Z7K5ZG7/graph.json","fetch_events":"https://pith.science/api/pith-number/PQURVD7WDMUCXDVVB67Z7K5ZG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7/action/storage_attestation","attest_author":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7/action/author_attestation","sign_citation":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7/action/citation_signature","submit_replication":"https://pith.science/pith/PQURVD7WDMUCXDVVB67Z7K5ZG7/action/replication_record"}},"created_at":"2026-07-05T11:51:23.088151+00:00","updated_at":"2026-07-05T11:51:23.088151+00:00"}