{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CMJIYLIEDJLKZINCXUBNY4ASYI","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":"50b70a00d58b3567768dbd2180046bc2a7130c8e639cc9255f8fb98e8e7da727","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T17:58:47Z","title_canon_sha256":"85bae915b00fb73fb66afee6262c0c933b68959212bc6b0fb0da69ad01a3b369"},"schema_version":"1.0","source":{"id":"2507.10541","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10541","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10541v2","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10541","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"pith_short_12","alias_value":"CMJIYLIEDJLK","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"pith_short_16","alias_value":"CMJIYLIEDJLKZINC","created_at":"2026-07-05T11:37:26Z"},{"alias_kind":"pith_short_8","alias_value":"CMJIYLIE","created_at":"2026-07-05T11:37:26Z"}],"graph_snapshots":[{"event_id":"sha256:591a657da74ca3e6fe89e48778b108854301f431a3dc407c97fcdeae95e9122f","target":"graph","created_at":"2026-07-05T11:37:26Z","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/2507.10541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Large Reasoning Models (LRMs) have achieved remarkable progress on task-specific benchmarks, yet their evaluation methods remain constrained by isolated problem-solving paradigms. Existing benchmarks predominantly assess single-question reasoning through sequential testing, resulting critical limitations: (1) vulnerability to data contamination and less challenging (e.g., DeepSeek-R1 achieves 97.0% on MATH500), forcing costly creation of new questions with large human efforts, (2) failure to evaluate models under multi-context pressure, a key requirement for real-world deployment. To br","authors_text":"Conghui He, H. Vicky Zhao, Lijun Wu, Qiyao Sun, Qizhi Pei, Yu Li, Zhuoshi Pan, Zinan Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T17:58:47Z","title":"REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10541","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":"sha256:22ae7262f32996b39e03bca937f52517f905b85b91208f08f3a05f8c9fad2700","target":"record","created_at":"2026-07-05T11:37:26Z","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":"50b70a00d58b3567768dbd2180046bc2a7130c8e639cc9255f8fb98e8e7da727","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T17:58:47Z","title_canon_sha256":"85bae915b00fb73fb66afee6262c0c933b68959212bc6b0fb0da69ad01a3b369"},"schema_version":"1.0","source":{"id":"2507.10541","kind":"arxiv","version":2}},"canonical_sha256":"13128c2d041a56aca1a2bd02dc7012c219e8661058eb34ab7ee933aac1385e1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13128c2d041a56aca1a2bd02dc7012c219e8661058eb34ab7ee933aac1385e1b","first_computed_at":"2026-07-05T11:37:26.894054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:26.894054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MqmpSZ/9K+qR1gmS6hBchh70Qyf6LqGmRdPZv48zNRmJqewcYzEYSQD+uYQ99MB83eulZm6tT+fj5QH5nQzzBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:26.894635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10541","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22ae7262f32996b39e03bca937f52517f905b85b91208f08f3a05f8c9fad2700","sha256:591a657da74ca3e6fe89e48778b108854301f431a3dc407c97fcdeae95e9122f"],"state_sha256":"38f4a708db1a03b4f64c63152a7355126a113a8287ba2422f9f1e1c1b57320ce"}