{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6VQMPOHQGPEXQCRNQUTUFWVRY7","short_pith_number":"pith:6VQMPOHQ","schema_version":"1.0","canonical_sha256":"f560c7b8f033c9780a2d852742dab1c7c580fafba9df795d5b15cf72ca0c4636","source":{"kind":"arxiv","id":"2504.14655","version":1},"attestation_state":"computed","paper":{"title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Huifeng Sun, Jason Klein Liu, Jian Hu, Siyue Wu, Wei Shen, Xiaolong Xu, Yan Wang, Yunhui Xia","submitted_at":"2025-04-20T15:28:16Z","abstract_excerpt":"We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focused coding benchmarks and self-contained training testbeds. By curating LeetCode Python problems with rich metadata, broad coverage, 100+ test cases per problem, and temporal splits (pre/post July 2024), our dataset enables contamination-free evaluation and efficient supervised fine-tuning (SFT). Experiments show reasoning models significantly outperform non-reasoning counterparts, while SFT with only 2.6K model-gene"},"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":"2504.14655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:28:16Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"82cf5e53496f420dff788d52a4e960bf3983c080be3c439b43ad2b2b76a9ce6e","abstract_canon_sha256":"09f7409deb1938f1a1f0966614bbe125fa2ba058ee8e3abcd0fea81369b93a55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:48.395618Z","signature_b64":"4DCSOXQSwPbINVt6E3wWbi/mbFjjHH1KzlV+Ex4+dxDiIVD3peTJGtKeYsZITNKt5l9qzrLXpASvFM8FtZ6mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f560c7b8f033c9780a2d852742dab1c7c580fafba9df795d5b15cf72ca0c4636","last_reissued_at":"2026-07-05T10:51:48.395082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:48.395082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Huifeng Sun, Jason Klein Liu, Jian Hu, Siyue Wu, Wei Shen, Xiaolong Xu, Yan Wang, Yunhui Xia","submitted_at":"2025-04-20T15:28:16Z","abstract_excerpt":"We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focused coding benchmarks and self-contained training testbeds. By curating LeetCode Python problems with rich metadata, broad coverage, 100+ test cases per problem, and temporal splits (pre/post July 2024), our dataset enables contamination-free evaluation and efficient supervised fine-tuning (SFT). Experiments show reasoning models significantly outperform non-reasoning counterparts, while SFT with only 2.6K model-gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14655","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/2504.14655/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":"2504.14655","created_at":"2026-07-05T10:51:48.395149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14655v1","created_at":"2026-07-05T10:51:48.395149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14655","created_at":"2026-07-05T10:51:48.395149+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VQMPOHQGPEX","created_at":"2026-07-05T10:51:48.395149+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VQMPOHQGPEXQCRN","created_at":"2026-07-05T10:51:48.395149+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VQMPOHQ","created_at":"2026-07-05T10:51:48.395149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25178","citing_title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31725","citing_title":"Do Machines Struggle Where Humans Do? LLM and Human Comprehension of Obfuscated Code","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23488","citing_title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25178","citing_title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26842","citing_title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18822","citing_title":"Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17958","citing_title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01379","citing_title":"Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model Strengths","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18471","citing_title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22312","citing_title":"Skywork Open Reasoner 1 Technical Report","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16322","citing_title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14539","citing_title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29957","citing_title":"Think Anywhere in Code Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23488","citing_title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06111","citing_title":"Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12268","citing_title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07725","citing_title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05963","citing_title":"QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7","json":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7.json","graph_json":"https://pith.science/api/pith-number/6VQMPOHQGPEXQCRNQUTUFWVRY7/graph.json","events_json":"https://pith.science/api/pith-number/6VQMPOHQGPEXQCRNQUTUFWVRY7/events.json","paper":"https://pith.science/paper/6VQMPOHQ"},"agent_actions":{"view_html":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7","download_json":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7.json","view_paper":"https://pith.science/paper/6VQMPOHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14655&json=true","fetch_graph":"https://pith.science/api/pith-number/6VQMPOHQGPEXQCRNQUTUFWVRY7/graph.json","fetch_events":"https://pith.science/api/pith-number/6VQMPOHQGPEXQCRNQUTUFWVRY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7/action/storage_attestation","attest_author":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7/action/author_attestation","sign_citation":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7/action/citation_signature","submit_replication":"https://pith.science/pith/6VQMPOHQGPEXQCRNQUTUFWVRY7/action/replication_record"}},"created_at":"2026-07-05T10:51:48.395149+00:00","updated_at":"2026-07-05T10:51:48.395149+00:00"}