{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DJKUWPK3V6SOBOR6GK2JASRZ4T","short_pith_number":"pith:DJKUWPK3","schema_version":"1.0","canonical_sha256":"1a554b3d5bafa4e0ba3e32b4904a39e4d9d7d0a044d52c3f7fe7f0f4c8ed73f9","source":{"kind":"arxiv","id":"2606.20227","version":1},"attestation_state":"computed","paper":{"title":"QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Kailong Wang, Ling Shi, Lorenz Goette, Tianlong Yu, Xinyi Zheng, Yongxin Zhao","submitted_at":"2026-06-18T13:40:27Z","abstract_excerpt":"Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency.\n  To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conj"},"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":"2606.20227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T13:40:27Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"89de1a6d356ee9dc2b71f4b567663214765c9707616ff8967d635ec831996b92","abstract_canon_sha256":"5a27ecbf30e3e49a2a03f06e08ea9551e9a86cc379efa7286a00c24619be3a1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:06.383041Z","signature_b64":"eVfxInDhEM+vBj/Yb2gnecfdAJFSvHi/Un5PFfGOQR/g71Ya3KRcykfI5qzt6KATp7us0su84xuEy4LEF+IvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a554b3d5bafa4e0ba3e32b4904a39e4d9d7d0a044d52c3f7fe7f0f4c8ed73f9","last_reissued_at":"2026-06-19T16:13:06.382646Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:06.382646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Kailong Wang, Ling Shi, Lorenz Goette, Tianlong Yu, Xinyi Zheng, Yongxin Zhao","submitted_at":"2026-06-18T13:40:27Z","abstract_excerpt":"Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency.\n  To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20227","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/2606.20227/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":"2606.20227","created_at":"2026-06-19T16:13:06.382709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20227v1","created_at":"2026-06-19T16:13:06.382709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20227","created_at":"2026-06-19T16:13:06.382709+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJKUWPK3V6SO","created_at":"2026-06-19T16:13:06.382709+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJKUWPK3V6SOBOR6","created_at":"2026-06-19T16:13:06.382709+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJKUWPK3","created_at":"2026-06-19T16:13:06.382709+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/DJKUWPK3V6SOBOR6GK2JASRZ4T","json":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T.json","graph_json":"https://pith.science/api/pith-number/DJKUWPK3V6SOBOR6GK2JASRZ4T/graph.json","events_json":"https://pith.science/api/pith-number/DJKUWPK3V6SOBOR6GK2JASRZ4T/events.json","paper":"https://pith.science/paper/DJKUWPK3"},"agent_actions":{"view_html":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T","download_json":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T.json","view_paper":"https://pith.science/paper/DJKUWPK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20227&json=true","fetch_graph":"https://pith.science/api/pith-number/DJKUWPK3V6SOBOR6GK2JASRZ4T/graph.json","fetch_events":"https://pith.science/api/pith-number/DJKUWPK3V6SOBOR6GK2JASRZ4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T/action/storage_attestation","attest_author":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T/action/author_attestation","sign_citation":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T/action/citation_signature","submit_replication":"https://pith.science/pith/DJKUWPK3V6SOBOR6GK2JASRZ4T/action/replication_record"}},"created_at":"2026-06-19T16:13:06.382709+00:00","updated_at":"2026-06-19T16:13:06.382709+00:00"}