{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2FUKPHJKSQNLAKVQA36QLITKZN","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":"c6b2922d4d9f0af0ee1845d50b328e4bb7385d2d63b8505233ecb9bd0c760b31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T16:46:36Z","title_canon_sha256":"3770977b9a2f510cbc05bd9284037807c6dac18b5d671b3e81f42c3a50847c16"},"schema_version":"1.0","source":{"id":"2606.29493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29493","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29493v1","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29493","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"2FUKPHJKSQNL","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"2FUKPHJKSQNLAKVQ","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"2FUKPHJK","created_at":"2026-06-30T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:3721128276f1acc229febcdffc088dba4759b1df94ae316992ceb8149ddfcf9f","target":"graph","created_at":"2026-06-30T01:18:08Z","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/2606.29493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof. However, the kernel only checks that a proof establishes a \\emph{formal} statement; it does not verify that the statement faithfully encodes the intended informal problem, nor that evaluation harnesses are robust to trivial or adversarial solutions. We audit five widely used Lean theorem-proving benchmarks and their forks, using corpus-scale static checkers to surface 4,833 findings, including 398 mechanically certified issues such as","authors_text":"Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T16:46:36Z","title":"Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29493","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":"sha256:6643010536fc3916b7bf60658a81f3d5ad9ec3db79e174072f1bddda59d3acc4","target":"record","created_at":"2026-06-30T01:18:08Z","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":"c6b2922d4d9f0af0ee1845d50b328e4bb7385d2d63b8505233ecb9bd0c760b31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T16:46:36Z","title_canon_sha256":"3770977b9a2f510cbc05bd9284037807c6dac18b5d671b3e81f42c3a50847c16"},"schema_version":"1.0","source":{"id":"2606.29493","kind":"arxiv","version":1}},"canonical_sha256":"d168a79d2a941ab02ab006fd05a26acb5ce63b3406743192b4e3a2e054c06b34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d168a79d2a941ab02ab006fd05a26acb5ce63b3406743192b4e3a2e054c06b34","first_computed_at":"2026-06-30T01:18:08.914938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:08.914938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ntfOpF3AMkIOE3FGqusRs0QhMPf9xvKh5Mo2OQq5SktxeCCxoJiJjKe8TSJ5iPMjEKnU++ASI1lMtGO9xJZFAQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:08.915563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6643010536fc3916b7bf60658a81f3d5ad9ec3db79e174072f1bddda59d3acc4","sha256:3721128276f1acc229febcdffc088dba4759b1df94ae316992ceb8149ddfcf9f"],"state_sha256":"506012e77d2d4de3206fa4341816136520dbdd7afec3c21f0ea67651153b73dc"}