{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCZAP76H4OJ6AB6LSCK6XE3SDU","short_pith_number":"pith:GCZAP76H","schema_version":"1.0","canonical_sha256":"30b207ffc7e393e007cb9095eb93721d325d238991c804d6d783245307dd55eb","source":{"kind":"arxiv","id":"2506.05817","version":1},"attestation_state":"computed","paper":{"title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Hongyan Li, Kai Shen, Siyao Liu, Yang Sun, Zihan Wang","submitted_at":"2025-06-06T07:29:01Z","abstract_excerpt":"Competitive programming, due to its high reasoning difficulty and precise correctness feedback, has become a key task for both training and evaluating the reasoning capabilities of large language models (LLMs). However, while a large amount of public problem data, such as problem statements and solutions, is available, the test cases of these problems are often difficult to obtain. Therefore, test case generation is a necessary task for building large-scale datasets, and the quality of the test cases directly determines the accuracy of the evaluation. In this paper, we introduce an LLM-based a"},"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":"2506.05817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-06T07:29:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"07f667dadf2db5aa02084ea999560e1b07cbd49df3fcae7932d896e7bc61c169","abstract_canon_sha256":"8256a88364a84cd9d4aebd9db23dfbc354272f8b35eed732203baaae7e36d560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:10.675611Z","signature_b64":"l5vsz0jBuAWICE5XsUGA+NvCo9qQprutstrE8fWYUKSG1X63wdJBrlgBA+FvOrqC/vs+XFPTpJNa88QyGUwrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b207ffc7e393e007cb9095eb93721d325d238991c804d6d783245307dd55eb","last_reissued_at":"2026-07-05T11:17:10.675041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:10.675041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Hongyan Li, Kai Shen, Siyao Liu, Yang Sun, Zihan Wang","submitted_at":"2025-06-06T07:29:01Z","abstract_excerpt":"Competitive programming, due to its high reasoning difficulty and precise correctness feedback, has become a key task for both training and evaluating the reasoning capabilities of large language models (LLMs). However, while a large amount of public problem data, such as problem statements and solutions, is available, the test cases of these problems are often difficult to obtain. Therefore, test case generation is a necessary task for building large-scale datasets, and the quality of the test cases directly determines the accuracy of the evaluation. In this paper, we introduce an LLM-based a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05817","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/2506.05817/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":"2506.05817","created_at":"2026-07-05T11:17:10.675118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05817v1","created_at":"2026-07-05T11:17:10.675118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05817","created_at":"2026-07-05T11:17:10.675118+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCZAP76H4OJ6","created_at":"2026-07-05T11:17:10.675118+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCZAP76H4OJ6AB6L","created_at":"2026-07-05T11:17:10.675118+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCZAP76H","created_at":"2026-07-05T11:17:10.675118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25450","citing_title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25450","citing_title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09711","citing_title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28751","citing_title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17526","citing_title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15301","citing_title":"Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15229","citing_title":"VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16321","citing_title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02721","citing_title":"GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02776","citing_title":"Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11235","citing_title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08553","citing_title":"VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06755","citing_title":"Babbling Suppression: Making LLMs Greener One Token at a Time","ref_index":44,"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":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU","json":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU.json","graph_json":"https://pith.science/api/pith-number/GCZAP76H4OJ6AB6LSCK6XE3SDU/graph.json","events_json":"https://pith.science/api/pith-number/GCZAP76H4OJ6AB6LSCK6XE3SDU/events.json","paper":"https://pith.science/paper/GCZAP76H"},"agent_actions":{"view_html":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU","download_json":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU.json","view_paper":"https://pith.science/paper/GCZAP76H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05817&json=true","fetch_graph":"https://pith.science/api/pith-number/GCZAP76H4OJ6AB6LSCK6XE3SDU/graph.json","fetch_events":"https://pith.science/api/pith-number/GCZAP76H4OJ6AB6LSCK6XE3SDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU/action/storage_attestation","attest_author":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU/action/author_attestation","sign_citation":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU/action/citation_signature","submit_replication":"https://pith.science/pith/GCZAP76H4OJ6AB6LSCK6XE3SDU/action/replication_record"}},"created_at":"2026-07-05T11:17:10.675118+00:00","updated_at":"2026-07-05T11:17:10.675118+00:00"}