{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WALU5PW2SN3KKH5HLNHDSNJKTZ","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":"7022bf24598c08051a4293ca102d3879f5dcb74d4cb4007eef58fc6eb0cb869e","cross_cats_sorted":["cs.CL","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T11:59:28Z","title_canon_sha256":"39085c431845fde385cb9036c79112693b2b9d5891d971021b950a81dd4db57d"},"schema_version":"1.0","source":{"id":"2605.28365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28365","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28365v1","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28365","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"WALU5PW2SN3K","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"WALU5PW2SN3KKH5H","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"WALU5PW2","created_at":"2026-05-28T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:ec0b443cb1599f92a41f942c9b7da913d7f9599863cd4ecfb5239fbc92815838","target":"graph","created_at":"2026-05-28T01:05:16Z","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/2605.28365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lean is increasingly used to judge natural-language mathematical answers, but its signal is partial: many answers never formalize, and a failed proof may reflect an ill-typed statement or a missing library fact, not a wrong answer. On MATH-500 we show this signal is (i) sharply coverage-dependent, that is the proof-winning answer is correct 96% of the time at high proved coverage but 20% at low, and (ii) sparse and often unfaithful: a 7B autoformalizer proves a class for only 28% of problems, and a manual audit finds only approximately 43% of those proofs faithful. We propose COVCAL, a selecto","authors_text":"Haitham Bou Ammar, Matthieu Zimmer, Pauline Bourigault, Rasul Tutunov, Xiaotong Ji","cross_cats":["cs.CL","cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T11:59:28Z","title":"Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28365","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":"sha256:7cce6cd964c290f336f7b251d4d349a04bd5714921560cd35e5e49e635337b72","target":"record","created_at":"2026-05-28T01:05:16Z","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":"7022bf24598c08051a4293ca102d3879f5dcb74d4cb4007eef58fc6eb0cb869e","cross_cats_sorted":["cs.CL","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T11:59:28Z","title_canon_sha256":"39085c431845fde385cb9036c79112693b2b9d5891d971021b950a81dd4db57d"},"schema_version":"1.0","source":{"id":"2605.28365","kind":"arxiv","version":1}},"canonical_sha256":"b0174ebeda9376a51fa75b4e39352a9e704090ef5ab033bc4a3cf3ccc40348b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0174ebeda9376a51fa75b4e39352a9e704090ef5ab033bc4a3cf3ccc40348b8","first_computed_at":"2026-05-28T01:05:16.058666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:16.058666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2K9jZBQP1PEqGH3YJn4SqDYpc+uPstezC6/zvWKkgE9UJEtab6cP2vpIml8wDuxRdsNzsXe6Gq9l83+TPUNQDw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:16.059088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cce6cd964c290f336f7b251d4d349a04bd5714921560cd35e5e49e635337b72","sha256:ec0b443cb1599f92a41f942c9b7da913d7f9599863cd4ecfb5239fbc92815838"],"state_sha256":"384f2bae9a7137d3fe1c0a024b2d21c01e0cc4769f73abc1263b6be7587356cc"}