{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3X6HCVDMLG2Y4TSOXCQY7PVEEY","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":"4345d3ecad4f88d508b1398a9bb027556d0667679b12c2a1638abd595bbf1771","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T16:52:52Z","title_canon_sha256":"c1eefae64a663a692bd4767b3aa27c0fa66dccf486113c24f0860ff5ab75b8cc"},"schema_version":"1.0","source":{"id":"2602.24173","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.24173","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2602.24173v2","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.24173","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"3X6HCVDMLG2Y","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"3X6HCVDMLG2Y4TSO","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"3X6HCVDM","created_at":"2026-06-23T03:13:54Z"}],"graph_snapshots":[{"event_id":"sha256:e4c058feac348425804d31782813635a47ba05e10701668f4119e264fca8a710","target":"graph","created_at":"2026-06-23T03:13:54Z","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/2602.24173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on static, hand-curated sets of contest or textbook-style problems as proxies for mathematical research. Instead, we establish an updatable benchmark evaluating models directly on the latest research results in mathematics. This consists of an automatic pipeline that extracts lemmas from arXiv and rewrites them into self-contained statements by making all assumptions and required definitions explicit. It results in a benchmark that can be updated re","authors_text":"Amaury Hayat, Antoine Peyronnet, Fabian Gloeckle","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T16:52:52Z","title":"LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.24173","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":"sha256:2129c1e5ab98a069dd587e6144de7c373700d9851c850415c8e7e942727615ee","target":"record","created_at":"2026-06-23T03:13:54Z","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":"4345d3ecad4f88d508b1398a9bb027556d0667679b12c2a1638abd595bbf1771","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T16:52:52Z","title_canon_sha256":"c1eefae64a663a692bd4767b3aa27c0fa66dccf486113c24f0860ff5ab75b8cc"},"schema_version":"1.0","source":{"id":"2602.24173","kind":"arxiv","version":2}},"canonical_sha256":"ddfc71546c59b58e4e4eb8a18fbea426389dfe32bda3ac6a1742cbe979bb1998","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddfc71546c59b58e4e4eb8a18fbea426389dfe32bda3ac6a1742cbe979bb1998","first_computed_at":"2026-06-23T03:13:54.868408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:54.868408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jDTQJGvjslN2YX/QgUuAXosi5TL4plDlIxy9wBcalRIGxU6KUgoAFf/pLdqL+GCdw4i134eZY3qqtmyH9aJsDw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:54.868871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.24173","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2129c1e5ab98a069dd587e6144de7c373700d9851c850415c8e7e942727615ee","sha256:e4c058feac348425804d31782813635a47ba05e10701668f4119e264fca8a710"],"state_sha256":"78610c730b7aed8d2373791a4741c209c16e4fb2e18701b3a41d5e82ab6f1fae"}