{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5PJOE3OJOYEIXGL6LRLJQW7VFK","short_pith_number":"pith:5PJOE3OJ","schema_version":"1.0","canonical_sha256":"ebd2e26dc976088b997e5c56985bf52aabf13cb7fe5b1b75b4ab9ac020f4c8e4","source":{"kind":"arxiv","id":"2412.18989","version":2},"attestation_state":"computed","paper":{"title":"How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alejandro Velasco, Daniel Rodriguez-Cardenas, David N. Palacio, Denys Poshyvanyk, Luftar Rahman Alif","submitted_at":"2024-12-25T21:56:35Z","abstract_excerpt":"Large Language Models (LLMs) have shown significant potential in automating software engineering tasks, particularly in code generation. However, current evaluation benchmarks, which primarily focus on accuracy, fall short in assessing the quality of the code generated by these models, specifically their tendency to produce code smells. To address this limitation, we introduce CodeSmellEval, a benchmark designed to evaluate the propensity of LLMs for generating code smells. Our benchmark includes a novel metric: Propensity Smelly Score (PSC), and a curated dataset of method-level code smells: "},"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":"2412.18989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-25T21:56:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"926c431e8b290fece088f12386f64301b1a468d18616fa29d0da02b1d56065bb","abstract_canon_sha256":"55d970132df2daa2d277de841810157cec090f5d5de4fe4cef861453898e174a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:56.770716Z","signature_b64":"j78/pHq1ToC66cySZ+TZ4kSd75iU8WT04tIb2GFH6p7RV03ClB8S+ibAWDJSy1NCD1souLOEQBbOGWX38FgnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebd2e26dc976088b997e5c56985bf52aabf13cb7fe5b1b75b4ab9ac020f4c8e4","last_reissued_at":"2026-07-05T10:02:56.770135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:56.770135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alejandro Velasco, Daniel Rodriguez-Cardenas, David N. Palacio, Denys Poshyvanyk, Luftar Rahman Alif","submitted_at":"2024-12-25T21:56:35Z","abstract_excerpt":"Large Language Models (LLMs) have shown significant potential in automating software engineering tasks, particularly in code generation. However, current evaluation benchmarks, which primarily focus on accuracy, fall short in assessing the quality of the code generated by these models, specifically their tendency to produce code smells. To address this limitation, we introduce CodeSmellEval, a benchmark designed to evaluate the propensity of LLMs for generating code smells. Our benchmark includes a novel metric: Propensity Smelly Score (PSC), and a curated dataset of method-level code smells: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18989","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/2412.18989/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":"2412.18989","created_at":"2026-07-05T10:02:56.770219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18989v2","created_at":"2026-07-05T10:02:56.770219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18989","created_at":"2026-07-05T10:02:56.770219+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PJOE3OJOYEI","created_at":"2026-07-05T10:02:56.770219+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PJOE3OJOYEIXGL6","created_at":"2026-07-05T10:02:56.770219+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PJOE3OJ","created_at":"2026-07-05T10:02:56.770219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK","json":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK.json","graph_json":"https://pith.science/api/pith-number/5PJOE3OJOYEIXGL6LRLJQW7VFK/graph.json","events_json":"https://pith.science/api/pith-number/5PJOE3OJOYEIXGL6LRLJQW7VFK/events.json","paper":"https://pith.science/paper/5PJOE3OJ"},"agent_actions":{"view_html":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK","download_json":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK.json","view_paper":"https://pith.science/paper/5PJOE3OJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18989&json=true","fetch_graph":"https://pith.science/api/pith-number/5PJOE3OJOYEIXGL6LRLJQW7VFK/graph.json","fetch_events":"https://pith.science/api/pith-number/5PJOE3OJOYEIXGL6LRLJQW7VFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK/action/storage_attestation","attest_author":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK/action/author_attestation","sign_citation":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK/action/citation_signature","submit_replication":"https://pith.science/pith/5PJOE3OJOYEIXGL6LRLJQW7VFK/action/replication_record"}},"created_at":"2026-07-05T10:02:56.770219+00:00","updated_at":"2026-07-05T10:02:56.770219+00:00"}