{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UQXNQCHGLMGUIYKVIVHRXNA6BZ","short_pith_number":"pith:UQXNQCHG","schema_version":"1.0","canonical_sha256":"a42ed808e65b0d446155454f1bb41e0e638356f3fc35bf9eca427be64f7db181","source":{"kind":"arxiv","id":"2502.20868","version":1},"attestation_state":"computed","paper":{"title":"ProBench: Benchmarking Large Language Models in Competitive Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Jianxiang Peng, Lei Yang, Ling Shi, Renren Jin, Yue Chen","submitted_at":"2025-02-28T09:12:42Z","abstract_excerpt":"With reasoning language models such as OpenAI-o3 and DeepSeek-R1 emerging, large language models (LLMs) have entered a new phase of development. However, existing benchmarks for coding evaluation are gradually inadequate to assess the capability of advanced LLMs in code reasoning. To bridge the gap for high-level code reasoning assessment, we propose ProBench to benchmark LLMs in competitive programming, drawing inspiration from the International Collegiate Programming Contest. ProBench collects a comprehensive set of competitive programming problems from Codeforces, Luogu, and Nowcoder platfo"},"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":"2502.20868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T09:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"c5f65438c05efeb772d3c71c6afb76ea992e83108784085a8a39de05175a29c1","abstract_canon_sha256":"b2b8500709567920e343637dcd377c461ba804ee85db4aa9c4977c8826b5dcea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:41.417009Z","signature_b64":"Y+uV5tzJuwJYqTub3L/OqPTkx9z7VzfDDtJM26hVzzm3dneDxmNMhIXBFEjvyXBXZAUDINUhYcpDpoqcHYvXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a42ed808e65b0d446155454f1bb41e0e638356f3fc35bf9eca427be64f7db181","last_reissued_at":"2026-07-05T10:21:41.416488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:41.416488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProBench: Benchmarking Large Language Models in Competitive Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Jianxiang Peng, Lei Yang, Ling Shi, Renren Jin, Yue Chen","submitted_at":"2025-02-28T09:12:42Z","abstract_excerpt":"With reasoning language models such as OpenAI-o3 and DeepSeek-R1 emerging, large language models (LLMs) have entered a new phase of development. However, existing benchmarks for coding evaluation are gradually inadequate to assess the capability of advanced LLMs in code reasoning. To bridge the gap for high-level code reasoning assessment, we propose ProBench to benchmark LLMs in competitive programming, drawing inspiration from the International Collegiate Programming Contest. ProBench collects a comprehensive set of competitive programming problems from Codeforces, Luogu, and Nowcoder platfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20868","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/2502.20868/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":"2502.20868","created_at":"2026-07-05T10:21:41.416539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20868v1","created_at":"2026-07-05T10:21:41.416539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20868","created_at":"2026-07-05T10:21:41.416539+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQXNQCHGLMGU","created_at":"2026-07-05T10:21:41.416539+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQXNQCHGLMGUIYKV","created_at":"2026-07-05T10:21:41.416539+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQXNQCHG","created_at":"2026-07-05T10:21:41.416539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00062","citing_title":"AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02188","citing_title":"Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02721","citing_title":"GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02431","citing_title":"ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ","json":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ.json","graph_json":"https://pith.science/api/pith-number/UQXNQCHGLMGUIYKVIVHRXNA6BZ/graph.json","events_json":"https://pith.science/api/pith-number/UQXNQCHGLMGUIYKVIVHRXNA6BZ/events.json","paper":"https://pith.science/paper/UQXNQCHG"},"agent_actions":{"view_html":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ","download_json":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ.json","view_paper":"https://pith.science/paper/UQXNQCHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20868&json=true","fetch_graph":"https://pith.science/api/pith-number/UQXNQCHGLMGUIYKVIVHRXNA6BZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UQXNQCHGLMGUIYKVIVHRXNA6BZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ/action/storage_attestation","attest_author":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ/action/author_attestation","sign_citation":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ/action/citation_signature","submit_replication":"https://pith.science/pith/UQXNQCHGLMGUIYKVIVHRXNA6BZ/action/replication_record"}},"created_at":"2026-07-05T10:21:41.416539+00:00","updated_at":"2026-07-05T10:21:41.416539+00:00"}