{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JVW23KQH57JX2ZOS5OQP43AAC3","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":"914040e8c9b01123e4d99e8593ce9b19e6147e4ed8dc8fa94a9477df98e6030c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T17:54:56Z","title_canon_sha256":"a4cbeb859acdbd571ba6ebf29e0f2754c4646e2e46132fdbee67f4c2de73193a"},"schema_version":"1.0","source":{"id":"2506.06877","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06877","created_at":"2026-07-05T11:26:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06877v2","created_at":"2026-07-05T11:26:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06877","created_at":"2026-07-05T11:26:31Z"},{"alias_kind":"pith_short_12","alias_value":"JVW23KQH57JX","created_at":"2026-07-05T11:26:31Z"},{"alias_kind":"pith_short_16","alias_value":"JVW23KQH57JX2ZOS","created_at":"2026-07-05T11:26:31Z"},{"alias_kind":"pith_short_8","alias_value":"JVW23KQH","created_at":"2026-07-05T11:26:31Z"}],"graph_snapshots":[{"event_id":"sha256:14ad1f494f0e1b5611ca7341f44dd821da672b5e3de642d42a715247a95065d4","target":"graph","created_at":"2026-07-05T11:26:31Z","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/2506.06877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Outcome-rewarded Large Language Models (LLMs) have demonstrated remarkable success in mathematical problem-solving. However, this success often masks a critical issue: models frequently achieve correct answers through fundamentally unsound reasoning processes, a phenomenon indicative of reward hacking. We introduce MathOlympiadEval, a new dataset with fine-grained annotations, which reveals a significant gap between LLMs' answer correctness and their low process correctness. Existing automated methods like LLM-as-a-judge struggle to reliably detect these reasoning flaws. To address this, we pr","authors_text":"Da Zheng, Jiaxing Guo, Lun Du, Shengzhong Zhang, Tongshan Xu, Wenjie Yang, Zengfeng Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T17:54:56Z","title":"Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06877","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":"sha256:626429ce9497535859522aba0a3d7e9ebf89e594a84d7fd044f94f227af38383","target":"record","created_at":"2026-07-05T11:26:31Z","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":"914040e8c9b01123e4d99e8593ce9b19e6147e4ed8dc8fa94a9477df98e6030c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T17:54:56Z","title_canon_sha256":"a4cbeb859acdbd571ba6ebf29e0f2754c4646e2e46132fdbee67f4c2de73193a"},"schema_version":"1.0","source":{"id":"2506.06877","kind":"arxiv","version":2}},"canonical_sha256":"4d6dadaa07efd37d65d2eba0fe6c0016e604092f30bd4735f5174c27b4951e5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d6dadaa07efd37d65d2eba0fe6c0016e604092f30bd4735f5174c27b4951e5f","first_computed_at":"2026-07-05T11:26:31.869071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:31.869071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"45t8ruWwt2lPsv8nW8WMUPvMwpL4Me5naTJchB8w67XJpeZS/xKgyPaf/DzE+eYymA8Aa/dgr2L9mBq0NRqVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:31.869535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06877","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:626429ce9497535859522aba0a3d7e9ebf89e594a84d7fd044f94f227af38383","sha256:14ad1f494f0e1b5611ca7341f44dd821da672b5e3de642d42a715247a95065d4"],"state_sha256":"45e9f4f4731a6510acf8e2962595f997204044e991484ac04c05acaf0a2411bd"}