{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6VQMPOHQGPEXQCRNQUTUFWVRY7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"09f7409deb1938f1a1f0966614bbe125fa2ba058ee8e3abcd0fea81369b93a55","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:28:16Z","title_canon_sha256":"82cf5e53496f420dff788d52a4e960bf3983c080be3c439b43ad2b2b76a9ce6e"},"schema_version":"1.0","source":{"id":"2504.14655","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14655","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14655v1","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14655","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"6VQMPOHQGPEX","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"6VQMPOHQGPEXQCRN","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"6VQMPOHQ","created_at":"2026-07-05T10:51:48Z"}],"graph_snapshots":[{"event_id":"sha256:ca9dd426eaf0fcf8fa4d338f607cb2bfbb773db0b9d9436b4ea438a67c295601","target":"graph","created_at":"2026-07-05T10:51:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.14655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huifeng Sun, Jason Klein Liu, Jian Hu, Siyue Wu, Wei Shen, Xiaolong Xu, Yan Wang, Yunhui Xia","cross_cats":["cs.CL","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:28:16Z","title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14655","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f57e40b13088d6767fda604c48998784291f3b602c58f78e5e743673d5cc197a","target":"record","created_at":"2026-07-05T10:51:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"09f7409deb1938f1a1f0966614bbe125fa2ba058ee8e3abcd0fea81369b93a55","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:28:16Z","title_canon_sha256":"82cf5e53496f420dff788d52a4e960bf3983c080be3c439b43ad2b2b76a9ce6e"},"schema_version":"1.0","source":{"id":"2504.14655","kind":"arxiv","version":1}},"canonical_sha256":"f560c7b8f033c9780a2d852742dab1c7c580fafba9df795d5b15cf72ca0c4636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f560c7b8f033c9780a2d852742dab1c7c580fafba9df795d5b15cf72ca0c4636","first_computed_at":"2026-07-05T10:51:48.395082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:48.395082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4DCSOXQSwPbINVt6E3wWbi/mbFjjHH1KzlV+Ex4+dxDiIVD3peTJGtKeYsZITNKt5l9qzrLXpASvFM8FtZ6mAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:48.395618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14655","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f57e40b13088d6767fda604c48998784291f3b602c58f78e5e743673d5cc197a","sha256:ca9dd426eaf0fcf8fa4d338f607cb2bfbb773db0b9d9436b4ea438a67c295601"],"state_sha256":"f8b82fc2386cfdc9a846a0959d7b5851599d6dc741d7f45a8f8934f0e2291556"}