{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6SPJWPFWX5TMLH43VFBSAKBC7J","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":"c8e61a481d2e6b315e1a2c0d914024141efc21d881568d72023020d14825b54b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T06:22:35Z","title_canon_sha256":"230331cf34d64926062c388d327599c6299c977b9f200dbe8a7481132c6d5c70"},"schema_version":"1.0","source":{"id":"2501.08613","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08613","created_at":"2026-07-05T12:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08613v3","created_at":"2026-07-05T12:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08613","created_at":"2026-07-05T12:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"6SPJWPFWX5TM","created_at":"2026-07-05T12:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"6SPJWPFWX5TMLH43","created_at":"2026-07-05T12:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"6SPJWPFW","created_at":"2026-07-05T12:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:fcc180f51bcc01ec1ba9efbe5f93e22610b3e75c1ddc6f12364570acc6e9cd4c","target":"graph","created_at":"2026-07-05T12:05:12Z","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/2501.08613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent successful paradigm of solving logical reasoning problems with tool-augmented large language models (LLMs) leverages translation of natural language (NL) statements into First-Order Logic~(FOL) and external theorem provers. However, the correctness of FOL statements, comprising operators and text, often go unverified due to the lack of a reliable evaluation metric for comparing generated and ground-truth FOLs. In this paper, we conduct a comprehensive study on the sensitivity of existing NL-, FOL-, and graph-based metrics to capture differences between a sampled FOL and its correspo","authors_text":"Ehsan Shareghi, Ramya Keerthy Thatikonda, Wray Buntine","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T06:22:35Z","title":"Assessing the Sensitivity and Alignment of FOL Closeness Metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08613","kind":"arxiv","version":3},"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:b53886c83f735652bb8d670c032249551dbc90bc6ab7f9b204861be6c84d8bc4","target":"record","created_at":"2026-07-05T12:05:12Z","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":"c8e61a481d2e6b315e1a2c0d914024141efc21d881568d72023020d14825b54b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T06:22:35Z","title_canon_sha256":"230331cf34d64926062c388d327599c6299c977b9f200dbe8a7481132c6d5c70"},"schema_version":"1.0","source":{"id":"2501.08613","kind":"arxiv","version":3}},"canonical_sha256":"f49e9b3cb6bf66c59f9ba943202822fa68167e39f991239a5b97db2de4750732","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f49e9b3cb6bf66c59f9ba943202822fa68167e39f991239a5b97db2de4750732","first_computed_at":"2026-07-05T12:05:12.307963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:12.307963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5Wn1mQcHzg9QXJIgzGfq1csWvHjK5/CYfVgBEcAqBhYItbZMiYD9yzrL4Pn7Mizja27qTqY12r44I1WXKuuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:12.308624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08613","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b53886c83f735652bb8d670c032249551dbc90bc6ab7f9b204861be6c84d8bc4","sha256:fcc180f51bcc01ec1ba9efbe5f93e22610b3e75c1ddc6f12364570acc6e9cd4c"],"state_sha256":"e9d90c4c4834deba8ae9146da39bf6cff41027b9fc337f642309a20551fe0583"}