{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KLYDHSRD63X2CLLHATPI2DJUCO","short_pith_number":"pith:KLYDHSRD","schema_version":"1.0","canonical_sha256":"52f033ca23f6efa12d6704de8d0d34139e172b2524e7311be9aacc61749465b1","source":{"kind":"arxiv","id":"2508.05710","version":2},"attestation_state":"computed","paper":{"title":"Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Fuzheng Zhang, Guorui Zhou, Hongzhi Zhang, Jia Fu, Jingyuan Zhang, Qi Wang, Xinyu Yang, Yahui Liu","submitted_at":"2025-08-07T07:36:01Z","abstract_excerpt":"Precise, correct feedback is crucial for effectively training large language models (LLMs) in code reinforcement learning. However, synthesizing high-quality test cases remains a profoundly challenging and unsolved problem. In this work, we present Klear-CodeTest, a comprehensive test case synthesis framework featuring rigorous verification to ensure quality and reliability of test cases. Our approach achieves broad coverage of programming problems via a novel Generator-Validation (G-V) framework, ensuring correctness through a consistency validation mechanism that verifies outputs against gol"},"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":"2508.05710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-08-07T07:36:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fcbf673f66ae370e7e4d3b934054089fd467b7b7041b8cee47f408cfdf4a7d72","abstract_canon_sha256":"662dd1d4cb3b2ddab2ab03be972ff7af4e337be4dc962494c6d0e44a1dc9b1aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:22.623026Z","signature_b64":"8qMs77tg1E5ZuR2t6/cwakvnozG22PdtcztPylHnam05IhiJmslhUODhVY+X8KB1nJ8KHakY5DxNyj7qmYcFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f033ca23f6efa12d6704de8d0d34139e172b2524e7311be9aacc61749465b1","last_reissued_at":"2026-07-05T12:09:22.622510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:22.622510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Fuzheng Zhang, Guorui Zhou, Hongzhi Zhang, Jia Fu, Jingyuan Zhang, Qi Wang, Xinyu Yang, Yahui Liu","submitted_at":"2025-08-07T07:36:01Z","abstract_excerpt":"Precise, correct feedback is crucial for effectively training large language models (LLMs) in code reinforcement learning. However, synthesizing high-quality test cases remains a profoundly challenging and unsolved problem. In this work, we present Klear-CodeTest, a comprehensive test case synthesis framework featuring rigorous verification to ensure quality and reliability of test cases. Our approach achieves broad coverage of programming problems via a novel Generator-Validation (G-V) framework, ensuring correctness through a consistency validation mechanism that verifies outputs against gol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05710","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/2508.05710/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":"2508.05710","created_at":"2026-07-05T12:09:22.622571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05710v2","created_at":"2026-07-05T12:09:22.622571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05710","created_at":"2026-07-05T12:09:22.622571+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLYDHSRD63X2","created_at":"2026-07-05T12:09:22.622571+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLYDHSRD63X2CLLH","created_at":"2026-07-05T12:09:22.622571+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLYDHSRD","created_at":"2026-07-05T12:09:22.622571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25450","citing_title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25450","citing_title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04809","citing_title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO","json":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO.json","graph_json":"https://pith.science/api/pith-number/KLYDHSRD63X2CLLHATPI2DJUCO/graph.json","events_json":"https://pith.science/api/pith-number/KLYDHSRD63X2CLLHATPI2DJUCO/events.json","paper":"https://pith.science/paper/KLYDHSRD"},"agent_actions":{"view_html":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO","download_json":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO.json","view_paper":"https://pith.science/paper/KLYDHSRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05710&json=true","fetch_graph":"https://pith.science/api/pith-number/KLYDHSRD63X2CLLHATPI2DJUCO/graph.json","fetch_events":"https://pith.science/api/pith-number/KLYDHSRD63X2CLLHATPI2DJUCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO/action/storage_attestation","attest_author":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO/action/author_attestation","sign_citation":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO/action/citation_signature","submit_replication":"https://pith.science/pith/KLYDHSRD63X2CLLHATPI2DJUCO/action/replication_record"}},"created_at":"2026-07-05T12:09:22.622571+00:00","updated_at":"2026-07-05T12:09:22.622571+00:00"}