{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3PQBIA7C4H657GEB2ZBC5LWEBI","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":"b9a2dac41c65e3f4ebd73beea47c7e3cfa007edbac9aa3c9570de8a4ea72d14a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T12:23:54Z","title_canon_sha256":"ff7d892b73d54963ffbdc5edf98ee5fbaebb83b2914678db46240c4f6f34ef7d"},"schema_version":"1.0","source":{"id":"2606.23238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23238","created_at":"2026-06-23T03:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23238v1","created_at":"2026-06-23T03:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23238","created_at":"2026-06-23T03:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"3PQBIA7C4H65","created_at":"2026-06-23T03:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"3PQBIA7C4H657GEB","created_at":"2026-06-23T03:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"3PQBIA7C","created_at":"2026-06-23T03:14:14Z"}],"graph_snapshots":[{"event_id":"sha256:75effecc81e2d81b4f2f153f745119b1cd43a95ee9c169158ab5b6e8d8d4a3dc","target":"graph","created_at":"2026-06-23T03:14:14Z","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/2606.23238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Logical reasoning is essential for reliable AI, yet existing benchmarks are largely first-order-logic-centric, focusing on object-level deduction over fixed predicates. This misses many realistic scenarios where models must reason over rules, predicates, functions, constraints, and decision procedures themselves. We introduce HOLMES (Higher-Order Logic Meets real-world Explainable Symbolic reasoning), the first real-world benchmark for higher-order symbolic reasoning in LLMs, containing 1379 instances. Built on higher-order logic, HOLMES pairs natural-language problems with HOL formalizations,","authors_text":"Chenpeng Wang, Haoxuan Li, Jundong Xu, Liangming Pan, Mingzhen Ju, YuCheng Wu, Yue Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T12:23:54Z","title":"HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23238","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":"sha256:48d09575ca2a2de068a50e48f965e0e2e9eb0f52317fede10cb1d8b19ffa3b83","target":"record","created_at":"2026-06-23T03:14:14Z","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":"b9a2dac41c65e3f4ebd73beea47c7e3cfa007edbac9aa3c9570de8a4ea72d14a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T12:23:54Z","title_canon_sha256":"ff7d892b73d54963ffbdc5edf98ee5fbaebb83b2914678db46240c4f6f34ef7d"},"schema_version":"1.0","source":{"id":"2606.23238","kind":"arxiv","version":1}},"canonical_sha256":"dbe01403e2e1fddf9881d6422eaec40a18e1ce6fe2111ba1b156200894c9d91e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbe01403e2e1fddf9881d6422eaec40a18e1ce6fe2111ba1b156200894c9d91e","first_computed_at":"2026-06-23T03:14:14.604784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:14.604784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aY+Z7s+tzEwJelIZGuTSs79PLZ6kPdIqW9GSqNuu4cBtb/H4bzbbRjl0ozX7xhDo3uX/1Vc1uWp9aOSWnAEJCg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:14.605173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48d09575ca2a2de068a50e48f965e0e2e9eb0f52317fede10cb1d8b19ffa3b83","sha256:75effecc81e2d81b4f2f153f745119b1cd43a95ee9c169158ab5b6e8d8d4a3dc"],"state_sha256":"2f6d2d0c8aabd87aa62d1d3f8458f49bf1c24552d7288a0e039296d49cef07e9"}