{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CEX5PKFGMBJKKT5BIBLNMFC4KZ","short_pith_number":"pith:CEX5PKFG","schema_version":"1.0","canonical_sha256":"112fd7a8a66052a54fa14056d6145c5650a2d65b9e7aa4847e1d653f7c0265f1","source":{"kind":"arxiv","id":"2504.16027","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking LLM for Code Smells Detection: OpenAI GPT-4.0 vs DeepSeek-V3","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Ahmed R. Sadik, Siddhata Govind","submitted_at":"2025-04-22T16:44:39Z","abstract_excerpt":"Determining the most effective Large Language Model for code smell detection presents a complex challenge. This study introduces a structured methodology and evaluation matrix to tackle this issue, leveraging a curated dataset of code samples consistently annotated with known smells. The dataset spans four prominent programming languages Java, Python, JavaScript, and C++; allowing for cross language comparison. We benchmark two state of the art LLMs, OpenAI GPT 4.0 and DeepSeek-V3, using precision, recall, and F1 score as evaluation metrics. Our analysis covers three levels of detail: overall "},"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":"2504.16027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-22T16:44:39Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PL"],"title_canon_sha256":"7d30c5a962440ba79b63507bb15a34eecaf34b2f4360d316bba1641511597c88","abstract_canon_sha256":"d7293a6a8666522514d77acf47dad742ea374bd6cc82b476920f0cc2afc4741c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:33.642570Z","signature_b64":"HFuA8p+XypKk3G0B7f+ARHA7ioFYCYAsXs+r4fcBqtAzL1wjrmC1SAdw8GOeGYbVocvFzer5jbIoeJiDDA+QBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"112fd7a8a66052a54fa14056d6145c5650a2d65b9e7aa4847e1d653f7c0265f1","last_reissued_at":"2026-07-05T10:52:33.642088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:33.642088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking LLM for Code Smells Detection: OpenAI GPT-4.0 vs DeepSeek-V3","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Ahmed R. Sadik, Siddhata Govind","submitted_at":"2025-04-22T16:44:39Z","abstract_excerpt":"Determining the most effective Large Language Model for code smell detection presents a complex challenge. This study introduces a structured methodology and evaluation matrix to tackle this issue, leveraging a curated dataset of code samples consistently annotated with known smells. The dataset spans four prominent programming languages Java, Python, JavaScript, and C++; allowing for cross language comparison. We benchmark two state of the art LLMs, OpenAI GPT 4.0 and DeepSeek-V3, using precision, recall, and F1 score as evaluation metrics. Our analysis covers three levels of detail: overall "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16027","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/2504.16027/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":"2504.16027","created_at":"2026-07-05T10:52:33.642141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16027v1","created_at":"2026-07-05T10:52:33.642141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16027","created_at":"2026-07-05T10:52:33.642141+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEX5PKFGMBJK","created_at":"2026-07-05T10:52:33.642141+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEX5PKFGMBJKKT5B","created_at":"2026-07-05T10:52:33.642141+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEX5PKFG","created_at":"2026-07-05T10:52:33.642141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.06475","citing_title":"Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10661","citing_title":"DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ","json":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ.json","graph_json":"https://pith.science/api/pith-number/CEX5PKFGMBJKKT5BIBLNMFC4KZ/graph.json","events_json":"https://pith.science/api/pith-number/CEX5PKFGMBJKKT5BIBLNMFC4KZ/events.json","paper":"https://pith.science/paper/CEX5PKFG"},"agent_actions":{"view_html":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ","download_json":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ.json","view_paper":"https://pith.science/paper/CEX5PKFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16027&json=true","fetch_graph":"https://pith.science/api/pith-number/CEX5PKFGMBJKKT5BIBLNMFC4KZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CEX5PKFGMBJKKT5BIBLNMFC4KZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ/action/storage_attestation","attest_author":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ/action/author_attestation","sign_citation":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ/action/citation_signature","submit_replication":"https://pith.science/pith/CEX5PKFGMBJKKT5BIBLNMFC4KZ/action/replication_record"}},"created_at":"2026-07-05T10:52:33.642141+00:00","updated_at":"2026-07-05T10:52:33.642141+00:00"}