{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OOTW34SW3BI7DHUXPAHKKJJYQI","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":"86007587b8ed32211d12c6170ec1da2e51a83805c3e5281e65ed2c25edc40805","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:54:18Z","title_canon_sha256":"3018e0c4a46a8436e4663bf757ce519028f2d60fa870b00dafdddaa31f316091"},"schema_version":"1.0","source":{"id":"2504.02810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02810","created_at":"2026-07-05T10:53:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02810v2","created_at":"2026-07-05T10:53:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02810","created_at":"2026-07-05T10:53:53Z"},{"alias_kind":"pith_short_12","alias_value":"OOTW34SW3BI7","created_at":"2026-07-05T10:53:53Z"},{"alias_kind":"pith_short_16","alias_value":"OOTW34SW3BI7DHUX","created_at":"2026-07-05T10:53:53Z"},{"alias_kind":"pith_short_8","alias_value":"OOTW34SW","created_at":"2026-07-05T10:53:53Z"}],"graph_snapshots":[{"event_id":"sha256:ab1850de9b7bbf4795455ad12ec9eff7e7b57f5294f649db5327f62ed92b5622","target":"graph","created_at":"2026-07-05T10:53:53Z","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/2504.02810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baizhou Huang, Haotian Ye, Haowei Lin, James Zou, Jianhua Zhu, Jianzhu Ma, Ruilin Yan, Xiangyu Wang, Yitao Liang, Zihao Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:54:18Z","title":"Generative Evaluation of Complex Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02810","kind":"arxiv","version":2},"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":"sha256:364da445767112748dbc82521d4a59fc6a3fb2a419e5a231110f41b4a610b43d","target":"record","created_at":"2026-07-05T10:53:53Z","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":"86007587b8ed32211d12c6170ec1da2e51a83805c3e5281e65ed2c25edc40805","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:54:18Z","title_canon_sha256":"3018e0c4a46a8436e4663bf757ce519028f2d60fa870b00dafdddaa31f316091"},"schema_version":"1.0","source":{"id":"2504.02810","kind":"arxiv","version":2}},"canonical_sha256":"73a76df256d851f19e97780ea52538821b9057f033aaec7aff06cefd61543166","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73a76df256d851f19e97780ea52538821b9057f033aaec7aff06cefd61543166","first_computed_at":"2026-07-05T10:53:53.700663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:53.700663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iKJPOB+eGG9IEPMFOsH8X2PoUBqwvzOtMJp8lLfv5Hmq3LOfS3eAbug7NBl/Hzq5gwIQkUyChKAr1notrW9pAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:53.701247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:364da445767112748dbc82521d4a59fc6a3fb2a419e5a231110f41b4a610b43d","sha256:ab1850de9b7bbf4795455ad12ec9eff7e7b57f5294f649db5327f62ed92b5622"],"state_sha256":"6fdec69a25a5e3668bfa335e80ac5e82c0f477d0d33c141b743e8bf4ddf7cde6"}