{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GCZX6QCALGEZZ6WFG34B57O5GK","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":"60012a3dbfcdd7220bc8d81ab43cbcc25e74f1cfe9de9b3cd3c67fddfeb86ed7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:57:18Z","title_canon_sha256":"00a27cd2fceb5ecdd8fb407be1f5de039320f316fd734c2ba4605df33fcbd246"},"schema_version":"1.0","source":{"id":"2606.09450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09450","created_at":"2026-06-09T02:08:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09450v1","created_at":"2026-06-09T02:08:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09450","created_at":"2026-06-09T02:08:49Z"},{"alias_kind":"pith_short_12","alias_value":"GCZX6QCALGEZ","created_at":"2026-06-09T02:08:49Z"},{"alias_kind":"pith_short_16","alias_value":"GCZX6QCALGEZZ6WF","created_at":"2026-06-09T02:08:49Z"},{"alias_kind":"pith_short_8","alias_value":"GCZX6QCA","created_at":"2026-06-09T02:08:49Z"}],"graph_snapshots":[{"event_id":"sha256:bbc7de4c0dbaba4da7b8f4330d688c7125a36686df2e00dc3e28565d85a58411","target":"graph","created_at":"2026-06-09T02:08:49Z","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/2606.09450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to capture how models behave on longer, more dependency-rich mathematical developments. We introduce TheoremBench, a Lean4 benchmark designed to evaluate theorem provers beyond contest settings. The benchmark is built from nearly one hundred classical theorems and is released in two complementary forms: a plain main version containing one target theorem per instance, and a premised version that expands each theorem into ","authors_text":"Andrey Galichin, Elvir Karimov, Ivan Oseledets, QuocViet Pham","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:57:18Z","title":"TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09450","kind":"arxiv","version":1},"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":"sha256:374e2a9804915141019e4b6a42ba12bcb8360b197d544ef2d692640dc243d545","target":"record","created_at":"2026-06-09T02:08:49Z","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":"60012a3dbfcdd7220bc8d81ab43cbcc25e74f1cfe9de9b3cd3c67fddfeb86ed7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:57:18Z","title_canon_sha256":"00a27cd2fceb5ecdd8fb407be1f5de039320f316fd734c2ba4605df33fcbd246"},"schema_version":"1.0","source":{"id":"2606.09450","kind":"arxiv","version":1}},"canonical_sha256":"30b37f404059899cfac536f81efddd328b9142b80f37b14327172dbd3642044b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b37f404059899cfac536f81efddd328b9142b80f37b14327172dbd3642044b","first_computed_at":"2026-06-09T02:08:49.253291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:49.253291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RGZFldQ7QW6TP3H6UiFiE64nkJJ6slIWzzH93AVdHCCGtslWvKeD9f6PrEt6lCfgFsfCRh6I/V/hT8B5Oci8Cw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:49.254217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:374e2a9804915141019e4b6a42ba12bcb8360b197d544ef2d692640dc243d545","sha256:bbc7de4c0dbaba4da7b8f4330d688c7125a36686df2e00dc3e28565d85a58411"],"state_sha256":"86f2e46b798dfdb7e29653dbe7a09a7a9bc3538de6a22d68412633ea50ce65a7"}