{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:POD2ZVUTJHNRKTR7QZ4BYEMCBS","short_pith_number":"pith:POD2ZVUT","schema_version":"1.0","canonical_sha256":"7b87acd69349db154e3f86781c11820cabfb0e267a005a295c7330925509775b","source":{"kind":"arxiv","id":"2402.10735","version":4},"attestation_state":"computed","paper":{"title":"Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Federico Ruggeri, John Dougrez-Lewis, Mahmud Elahi Akhter, Maria Liakata, Sebastian L\\\"obbers, Yulan He","submitted_at":"2024-02-16T14:52:05Z","abstract_excerpt":"Although LLMs have shown great performance on Mathematics and Coding related reasoning tasks, the reasoning capabilities of LLMs regarding other forms of reasoning are still an open problem. Here, we examine the issue of reasoning from the perspective of claim verification. We propose a framework designed to break down any claim paired with evidence into atomic reasoning types that are necessary for verification. We use this framework to create RECV, the first claim verification benchmark, incorporating real-world claims, to assess the deductive and abductive reasoning capabilities of LLMs. Th"},"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":"2402.10735","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T14:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"7432330898e297415c48a9659d9131fdfe7b130988be2b68d67c0b7332289fc7","abstract_canon_sha256":"65565d38e7fafa2f5fe46714c90bf2f88ca3813b83fef69a7e33cbd4c5d69dc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:06.447903Z","signature_b64":"Gu6Uj7jCVN68mxCGHkwfWJrgFCuRJZQQA/FmTs5eaQkhhoUI1cSwOv4ZSoJcUKK145pbbtGP6avEhS4a8YpTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b87acd69349db154e3f86781c11820cabfb0e267a005a295c7330925509775b","last_reissued_at":"2026-07-05T11:23:06.447417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:06.447417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Federico Ruggeri, John Dougrez-Lewis, Mahmud Elahi Akhter, Maria Liakata, Sebastian L\\\"obbers, Yulan He","submitted_at":"2024-02-16T14:52:05Z","abstract_excerpt":"Although LLMs have shown great performance on Mathematics and Coding related reasoning tasks, the reasoning capabilities of LLMs regarding other forms of reasoning are still an open problem. Here, we examine the issue of reasoning from the perspective of claim verification. We propose a framework designed to break down any claim paired with evidence into atomic reasoning types that are necessary for verification. We use this framework to create RECV, the first claim verification benchmark, incorporating real-world claims, to assess the deductive and abductive reasoning capabilities of LLMs. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10735","kind":"arxiv","version":4},"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/2402.10735/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":"2402.10735","created_at":"2026-07-05T11:23:06.447473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10735v4","created_at":"2026-07-05T11:23:06.447473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10735","created_at":"2026-07-05T11:23:06.447473+00:00"},{"alias_kind":"pith_short_12","alias_value":"POD2ZVUTJHNR","created_at":"2026-07-05T11:23:06.447473+00:00"},{"alias_kind":"pith_short_16","alias_value":"POD2ZVUTJHNRKTR7","created_at":"2026-07-05T11:23:06.447473+00:00"},{"alias_kind":"pith_short_8","alias_value":"POD2ZVUT","created_at":"2026-07-05T11:23:06.447473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.17590","citing_title":"MERIT: Modular Framework for Multimodal Misinformation Detection with Web-Grounded Reasoning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS","json":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS.json","graph_json":"https://pith.science/api/pith-number/POD2ZVUTJHNRKTR7QZ4BYEMCBS/graph.json","events_json":"https://pith.science/api/pith-number/POD2ZVUTJHNRKTR7QZ4BYEMCBS/events.json","paper":"https://pith.science/paper/POD2ZVUT"},"agent_actions":{"view_html":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS","download_json":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS.json","view_paper":"https://pith.science/paper/POD2ZVUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10735&json=true","fetch_graph":"https://pith.science/api/pith-number/POD2ZVUTJHNRKTR7QZ4BYEMCBS/graph.json","fetch_events":"https://pith.science/api/pith-number/POD2ZVUTJHNRKTR7QZ4BYEMCBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS/action/storage_attestation","attest_author":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS/action/author_attestation","sign_citation":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS/action/citation_signature","submit_replication":"https://pith.science/pith/POD2ZVUTJHNRKTR7QZ4BYEMCBS/action/replication_record"}},"created_at":"2026-07-05T11:23:06.447473+00:00","updated_at":"2026-07-05T11:23:06.447473+00:00"}