{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HBBRERYYYB3XUEEOYTH4AKJHZF","short_pith_number":"pith:HBBRERYY","schema_version":"1.0","canonical_sha256":"3843124718c0777a108ec4cfc02927c94b5ce0695583f3d69ec33d3e274d2b19","source":{"kind":"arxiv","id":"2502.15770","version":2},"attestation_state":"computed","paper":{"title":"Performance Review on LLM for solving leetcode problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chuanqi Shi, Hang Zheng, Lun Wang, Shaoshui Du, Xinyu Qiu, Yanxin Shen, Yixian Shen, Yiyi Tao","submitted_at":"2025-02-16T08:52:45Z","abstract_excerpt":"This paper presents a comprehensive performance evaluation of Large Language Models (LLMs) in solving programming challenges from Leetcode, a widely used platform for algorithm practice and technical interviews. We began by crawling the Leetcode website to collect a diverse set of problems encompassing various difficulty levels and topics. Using this dataset, we generated solutions with multiple LLMs, including GPT-4 and GPT-3.5-turbo (ChatGPT-turbo). The generated solutions were systematically evaluated for correctness and efficiency. We employed the pass@k metric to assess the success rates "},"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":"2502.15770","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-16T08:52:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"490172a9d21dd09e6b85d574cbdcea2b5ffc5c7929dbc87a494b2aa1eb1559d8","abstract_canon_sha256":"56b3906cfd72a46c7e6c27323955f90936c2f3ae47dd7fec59a3153037b32512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:14.139034Z","signature_b64":"OPJNv+uBzYgqNHO/063IZDzBCs++3pi0DlqmZQaMgBEwlWJbMT/lsBMyZuxP6iGKRuYTNdbsvoxiVwnZdmaFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3843124718c0777a108ec4cfc02927c94b5ce0695583f3d69ec33d3e274d2b19","last_reissued_at":"2026-07-05T10:22:14.138465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:14.138465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance Review on LLM for solving leetcode problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chuanqi Shi, Hang Zheng, Lun Wang, Shaoshui Du, Xinyu Qiu, Yanxin Shen, Yixian Shen, Yiyi Tao","submitted_at":"2025-02-16T08:52:45Z","abstract_excerpt":"This paper presents a comprehensive performance evaluation of Large Language Models (LLMs) in solving programming challenges from Leetcode, a widely used platform for algorithm practice and technical interviews. We began by crawling the Leetcode website to collect a diverse set of problems encompassing various difficulty levels and topics. Using this dataset, we generated solutions with multiple LLMs, including GPT-4 and GPT-3.5-turbo (ChatGPT-turbo). The generated solutions were systematically evaluated for correctness and efficiency. We employed the pass@k metric to assess the success rates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15770","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/2502.15770/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":"2502.15770","created_at":"2026-07-05T10:22:14.138529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15770v2","created_at":"2026-07-05T10:22:14.138529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15770","created_at":"2026-07-05T10:22:14.138529+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBBRERYYYB3X","created_at":"2026-07-05T10:22:14.138529+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBBRERYYYB3XUEEO","created_at":"2026-07-05T10:22:14.138529+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBBRERYY","created_at":"2026-07-05T10:22:14.138529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24381","citing_title":"On the Stability of Prompt Ranking in Large Language Model Evaluation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF","json":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF.json","graph_json":"https://pith.science/api/pith-number/HBBRERYYYB3XUEEOYTH4AKJHZF/graph.json","events_json":"https://pith.science/api/pith-number/HBBRERYYYB3XUEEOYTH4AKJHZF/events.json","paper":"https://pith.science/paper/HBBRERYY"},"agent_actions":{"view_html":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF","download_json":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF.json","view_paper":"https://pith.science/paper/HBBRERYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15770&json=true","fetch_graph":"https://pith.science/api/pith-number/HBBRERYYYB3XUEEOYTH4AKJHZF/graph.json","fetch_events":"https://pith.science/api/pith-number/HBBRERYYYB3XUEEOYTH4AKJHZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF/action/storage_attestation","attest_author":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF/action/author_attestation","sign_citation":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF/action/citation_signature","submit_replication":"https://pith.science/pith/HBBRERYYYB3XUEEOYTH4AKJHZF/action/replication_record"}},"created_at":"2026-07-05T10:22:14.138529+00:00","updated_at":"2026-07-05T10:22:14.138529+00:00"}