{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SPJWPFWX5TMLH43VFBSAKBC7J","short_pith_number":"pith:6SPJWPFW","schema_version":"1.0","canonical_sha256":"f49e9b3cb6bf66c59f9ba943202822fa68167e39f991239a5b97db2de4750732","source":{"kind":"arxiv","id":"2501.08613","version":3},"attestation_state":"computed","paper":{"title":"Assessing the Sensitivity and Alignment of FOL Closeness Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Ramya Keerthy Thatikonda, Wray Buntine","submitted_at":"2025-01-15T06:22:35Z","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"},"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":"2501.08613","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T06:22:35Z","cross_cats_sorted":[],"title_canon_sha256":"230331cf34d64926062c388d327599c6299c977b9f200dbe8a7481132c6d5c70","abstract_canon_sha256":"c8e61a481d2e6b315e1a2c0d914024141efc21d881568d72023020d14825b54b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:12.308624Z","signature_b64":"u5Wn1mQcHzg9QXJIgzGfq1csWvHjK5/CYfVgBEcAqBhYItbZMiYD9yzrL4Pn7Mizja27qTqY12r44I1WXKuuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f49e9b3cb6bf66c59f9ba943202822fa68167e39f991239a5b97db2de4750732","last_reissued_at":"2026-07-05T12:05:12.307963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:12.307963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Sensitivity and Alignment of FOL Closeness Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Ramya Keerthy Thatikonda, Wray Buntine","submitted_at":"2025-01-15T06:22:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08613","kind":"arxiv","version":3},"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/2501.08613/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":"2501.08613","created_at":"2026-07-05T12:05:12.308076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08613v3","created_at":"2026-07-05T12:05:12.308076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08613","created_at":"2026-07-05T12:05:12.308076+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SPJWPFWX5TM","created_at":"2026-07-05T12:05:12.308076+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SPJWPFWX5TMLH43","created_at":"2026-07-05T12:05:12.308076+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SPJWPFW","created_at":"2026-07-05T12:05:12.308076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09100","citing_title":"Logical Reasoning in Large Language Models: A Survey","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J","json":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J.json","graph_json":"https://pith.science/api/pith-number/6SPJWPFWX5TMLH43VFBSAKBC7J/graph.json","events_json":"https://pith.science/api/pith-number/6SPJWPFWX5TMLH43VFBSAKBC7J/events.json","paper":"https://pith.science/paper/6SPJWPFW"},"agent_actions":{"view_html":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J","download_json":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J.json","view_paper":"https://pith.science/paper/6SPJWPFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08613&json=true","fetch_graph":"https://pith.science/api/pith-number/6SPJWPFWX5TMLH43VFBSAKBC7J/graph.json","fetch_events":"https://pith.science/api/pith-number/6SPJWPFWX5TMLH43VFBSAKBC7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J/action/storage_attestation","attest_author":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J/action/author_attestation","sign_citation":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J/action/citation_signature","submit_replication":"https://pith.science/pith/6SPJWPFWX5TMLH43VFBSAKBC7J/action/replication_record"}},"created_at":"2026-07-05T12:05:12.308076+00:00","updated_at":"2026-07-05T12:05:12.308076+00:00"}