{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3PQBIA7C4H657GEB2ZBC5LWEBI","short_pith_number":"pith:3PQBIA7C","schema_version":"1.0","canonical_sha256":"dbe01403e2e1fddf9881d6422eaec40a18e1ce6fe2111ba1b156200894c9d91e","source":{"kind":"arxiv","id":"2606.23238","version":1},"attestation_state":"computed","paper":{"title":"HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenpeng Wang, Haoxuan Li, Jundong Xu, Liangming Pan, Mingzhen Ju, YuCheng Wu, Yue Yu","submitted_at":"2026-06-22T12:23:54Z","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,"},"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":"2606.23238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T12:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"ff7d892b73d54963ffbdc5edf98ee5fbaebb83b2914678db46240c4f6f34ef7d","abstract_canon_sha256":"b9a2dac41c65e3f4ebd73beea47c7e3cfa007edbac9aa3c9570de8a4ea72d14a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:14.605173Z","signature_b64":"aY+Z7s+tzEwJelIZGuTSs79PLZ6kPdIqW9GSqNuu4cBtb/H4bzbbRjl0ozX7xhDo3uX/1Vc1uWp9aOSWnAEJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe01403e2e1fddf9881d6422eaec40a18e1ce6fe2111ba1b156200894c9d91e","last_reissued_at":"2026-06-23T03:14:14.604784Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:14.604784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenpeng Wang, Haoxuan Li, Jundong Xu, Liangming Pan, Mingzhen Ju, YuCheng Wu, Yue Yu","submitted_at":"2026-06-22T12:23:54Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23238","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/2606.23238/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":"2606.23238","created_at":"2026-06-23T03:14:14.604842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23238v1","created_at":"2026-06-23T03:14:14.604842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23238","created_at":"2026-06-23T03:14:14.604842+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PQBIA7C4H65","created_at":"2026-06-23T03:14:14.604842+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PQBIA7C4H657GEB","created_at":"2026-06-23T03:14:14.604842+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PQBIA7C","created_at":"2026-06-23T03:14:14.604842+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/3PQBIA7C4H657GEB2ZBC5LWEBI","json":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI.json","graph_json":"https://pith.science/api/pith-number/3PQBIA7C4H657GEB2ZBC5LWEBI/graph.json","events_json":"https://pith.science/api/pith-number/3PQBIA7C4H657GEB2ZBC5LWEBI/events.json","paper":"https://pith.science/paper/3PQBIA7C"},"agent_actions":{"view_html":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI","download_json":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI.json","view_paper":"https://pith.science/paper/3PQBIA7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23238&json=true","fetch_graph":"https://pith.science/api/pith-number/3PQBIA7C4H657GEB2ZBC5LWEBI/graph.json","fetch_events":"https://pith.science/api/pith-number/3PQBIA7C4H657GEB2ZBC5LWEBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI/action/storage_attestation","attest_author":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI/action/author_attestation","sign_citation":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI/action/citation_signature","submit_replication":"https://pith.science/pith/3PQBIA7C4H657GEB2ZBC5LWEBI/action/replication_record"}},"created_at":"2026-06-23T03:14:14.604842+00:00","updated_at":"2026-06-23T03:14:14.604842+00:00"}