{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2FUKPHJKSQNLAKVQA36QLITKZN","short_pith_number":"pith:2FUKPHJK","schema_version":"1.0","canonical_sha256":"d168a79d2a941ab02ab006fd05a26acb5ce63b3406743192b4e3a2e054c06b34","source":{"kind":"arxiv","id":"2606.29493","version":1},"attestation_state":"computed","paper":{"title":"Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman","submitted_at":"2026-06-28T16:46:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.29493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T16:46:36Z","cross_cats_sorted":[],"title_canon_sha256":"3770977b9a2f510cbc05bd9284037807c6dac18b5d671b3e81f42c3a50847c16","abstract_canon_sha256":"c6b2922d4d9f0af0ee1845d50b328e4bb7385d2d63b8505233ecb9bd0c760b31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:08.915563Z","signature_b64":"ntfOpF3AMkIOE3FGqusRs0QhMPf9xvKh5Mo2OQq5SktxeCCxoJiJjKe8TSJ5iPMjEKnU++ASI1lMtGO9xJZFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d168a79d2a941ab02ab006fd05a26acb5ce63b3406743192b4e3a2e054c06b34","last_reissued_at":"2026-06-30T01:18:08.914938Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:08.914938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman","submitted_at":"2026-06-28T16:46:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29493","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.29493/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.29493","created_at":"2026-06-30T01:18:08.915029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29493v1","created_at":"2026-06-30T01:18:08.915029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29493","created_at":"2026-06-30T01:18:08.915029+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FUKPHJKSQNL","created_at":"2026-06-30T01:18:08.915029+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FUKPHJKSQNLAKVQ","created_at":"2026-06-30T01:18:08.915029+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FUKPHJK","created_at":"2026-06-30T01:18:08.915029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN","json":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN.json","graph_json":"https://pith.science/api/pith-number/2FUKPHJKSQNLAKVQA36QLITKZN/graph.json","events_json":"https://pith.science/api/pith-number/2FUKPHJKSQNLAKVQA36QLITKZN/events.json","paper":"https://pith.science/paper/2FUKPHJK"},"agent_actions":{"view_html":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN","download_json":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN.json","view_paper":"https://pith.science/paper/2FUKPHJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29493&json=true","fetch_graph":"https://pith.science/api/pith-number/2FUKPHJKSQNLAKVQA36QLITKZN/graph.json","fetch_events":"https://pith.science/api/pith-number/2FUKPHJKSQNLAKVQA36QLITKZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN/action/storage_attestation","attest_author":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN/action/author_attestation","sign_citation":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN/action/citation_signature","submit_replication":"https://pith.science/pith/2FUKPHJKSQNLAKVQA36QLITKZN/action/replication_record"}},"created_at":"2026-06-30T01:18:08.915029+00:00","updated_at":"2026-06-30T01:18:08.915029+00:00"}