{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X2ICAZ3NMGW5BUHCYHKPFODSRA","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":"83c532e906bb05d113776586f393d0e105071ef4b17c3a77483c94b1223a2ba4","cross_cats_sorted":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T03:40:01Z","title_canon_sha256":"aa640b3a4ebe50756c5935442b6cd6b1743d5e8f701d807bd538d7d1c96aaf47"},"schema_version":"1.0","source":{"id":"2602.03061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03061","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03061v2","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03061","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_12","alias_value":"X2ICAZ3NMGW5","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_16","alias_value":"X2ICAZ3NMGW5BUHC","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_8","alias_value":"X2ICAZ3N","created_at":"2026-07-21T01:21:42Z"}],"graph_snapshots":[{"event_id":"sha256:2b6ca3b2e31fde5dae2f8644a729f24d932e1e6bfc428f667f5f2335ea2888b9","target":"graph","created_at":"2026-07-21T01:21:42Z","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/2602.03061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and unstable rankings across platforms. On difficult problems, an LLM may fail to produce a correct final answer, yet still provide reliable pairwise comparison signals indicating which of two candidate solutions is better. We leverage this observation to design a statistically efficient evaluation framework that combines standard labeled outcomes with pairwise comparison signals obtained by having models judge auxiliary reasoning chain","authors_text":"Can Jin, Linjun Zhang, Ruijia Wu, Yang Zhou, Zhixian Zhang, Zihan Dong","cross_cats":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T03:40:01Z","title":"Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03061","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":"sha256:34eb3ee29862d2e06aea93131c762d3e3c7493577fb7927de74aa17ddc8a1a94","target":"record","created_at":"2026-07-21T01:21:42Z","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":"83c532e906bb05d113776586f393d0e105071ef4b17c3a77483c94b1223a2ba4","cross_cats_sorted":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T03:40:01Z","title_canon_sha256":"aa640b3a4ebe50756c5935442b6cd6b1743d5e8f701d807bd538d7d1c96aaf47"},"schema_version":"1.0","source":{"id":"2602.03061","kind":"arxiv","version":2}},"canonical_sha256":"be9020676d61add0d0e2c1d4f2b872882bb27660b9e8e805948f138eab6a5cb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be9020676d61add0d0e2c1d4f2b872882bb27660b9e8e805948f138eab6a5cb2","first_computed_at":"2026-07-21T01:21:42.827160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:42.827160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ID1p6IlZq8IKkQvphCSGsQD717f1Rvg4d/Bu+FbYiE/HgPH1n/UL36IdINlsHAE8b87QKWVxi7bnXh2aTsmhCw==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:42.828114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34eb3ee29862d2e06aea93131c762d3e3c7493577fb7927de74aa17ddc8a1a94","sha256:2b6ca3b2e31fde5dae2f8644a729f24d932e1e6bfc428f667f5f2335ea2888b9"],"state_sha256":"a821c8ee0a02a99d783613fb28a1967d9ec72554b10c664e15e9cff6fc2dad09"}