{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OOTW34SW3BI7DHUXPAHKKJJYQI","short_pith_number":"pith:OOTW34SW","schema_version":"1.0","canonical_sha256":"73a76df256d851f19e97780ea52538821b9057f033aaec7aff06cefd61543166","source":{"kind":"arxiv","id":"2504.02810","version":2},"attestation_state":"computed","paper":{"title":"Generative Evaluation of Complex Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Baizhou Huang, Haotian Ye, Haowei Lin, James Zou, Jianhua Zhu, Jianzhu Ma, Ruilin Yan, Xiangyu Wang, Yitao Liang, Zihao Wang","submitted_at":"2025-04-03T17:54:18Z","abstract_excerpt":"With powerful large language models (LLMs) demonstrating superhuman reasoning capabilities, a critical question arises: Do LLMs genuinely reason, or do they merely recall answers from their extensive, web-scraped training datasets? Publicly released benchmarks inevitably become contaminated once incorporated into subsequent LLM training sets, undermining their reliability as faithful assessments. To address this, we introduce KUMO, a generative evaluation framework designed specifically for assessing reasoning in LLMs. KUMO synergistically combines LLMs with symbolic engines to dynamically pro"},"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":"2504.02810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:54:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3018e0c4a46a8436e4663bf757ce519028f2d60fa870b00dafdddaa31f316091","abstract_canon_sha256":"86007587b8ed32211d12c6170ec1da2e51a83805c3e5281e65ed2c25edc40805"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:53.701247Z","signature_b64":"iKJPOB+eGG9IEPMFOsH8X2PoUBqwvzOtMJp8lLfv5Hmq3LOfS3eAbug7NBl/Hzq5gwIQkUyChKAr1notrW9pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73a76df256d851f19e97780ea52538821b9057f033aaec7aff06cefd61543166","last_reissued_at":"2026-07-05T10:53:53.700663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:53.700663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Evaluation of Complex Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Baizhou Huang, Haotian Ye, Haowei Lin, James Zou, Jianhua Zhu, Jianzhu Ma, Ruilin Yan, Xiangyu Wang, Yitao Liang, Zihao Wang","submitted_at":"2025-04-03T17:54:18Z","abstract_excerpt":"With powerful large language models (LLMs) demonstrating superhuman reasoning capabilities, a critical question arises: Do LLMs genuinely reason, or do they merely recall answers from their extensive, web-scraped training datasets? Publicly released benchmarks inevitably become contaminated once incorporated into subsequent LLM training sets, undermining their reliability as faithful assessments. To address this, we introduce KUMO, a generative evaluation framework designed specifically for assessing reasoning in LLMs. KUMO synergistically combines LLMs with symbolic engines to dynamically pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02810","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/2504.02810/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":"2504.02810","created_at":"2026-07-05T10:53:53.700727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02810v2","created_at":"2026-07-05T10:53:53.700727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02810","created_at":"2026-07-05T10:53:53.700727+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOTW34SW3BI7","created_at":"2026-07-05T10:53:53.700727+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOTW34SW3BI7DHUX","created_at":"2026-07-05T10:53:53.700727+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOTW34SW","created_at":"2026-07-05T10:53:53.700727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI","json":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI.json","graph_json":"https://pith.science/api/pith-number/OOTW34SW3BI7DHUXPAHKKJJYQI/graph.json","events_json":"https://pith.science/api/pith-number/OOTW34SW3BI7DHUXPAHKKJJYQI/events.json","paper":"https://pith.science/paper/OOTW34SW"},"agent_actions":{"view_html":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI","download_json":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI.json","view_paper":"https://pith.science/paper/OOTW34SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02810&json=true","fetch_graph":"https://pith.science/api/pith-number/OOTW34SW3BI7DHUXPAHKKJJYQI/graph.json","fetch_events":"https://pith.science/api/pith-number/OOTW34SW3BI7DHUXPAHKKJJYQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI/action/storage_attestation","attest_author":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI/action/author_attestation","sign_citation":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI/action/citation_signature","submit_replication":"https://pith.science/pith/OOTW34SW3BI7DHUXPAHKKJJYQI/action/replication_record"}},"created_at":"2026-07-05T10:53:53.700727+00:00","updated_at":"2026-07-05T10:53:53.700727+00:00"}