{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JR7GO27D6AG7P3Z67OORCO6F4B","short_pith_number":"pith:JR7GO27D","schema_version":"1.0","canonical_sha256":"4c7e676be3f00df7ef3efb9d113bc5e0631b9ffa52bddd9a3c6772340caffe7f","source":{"kind":"arxiv","id":"2502.10338","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan Bundy, Kwabena Nuamah, Liane Guillou, Nick Ferguson","submitted_at":"2025-02-14T17:55:43Z","abstract_excerpt":"Large Language Models (LLMs) excel in natural language tasks but still face challenges in Question Answering (QA) tasks requiring complex, multi-step reasoning. We outline the types of reasoning required in some of these tasks, and reframe them in terms of meta-level reasoning (akin to high-level strategic reasoning or planning) and object-level reasoning (embodied in lower-level tasks such as mathematical reasoning). Franklin, a novel dataset with requirements of meta- and object-level reasoning, is introduced and used along with three other datasets to evaluate four LLMs at question answerin"},"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":"2502.10338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:55:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8628b968406f76fc1de6a4da6cdeea8dea090993eb4d708cb69752246441a7c8","abstract_canon_sha256":"44576afbfb23a51a320d669e54de2b4016380cfda8fa8cb2c92b635b6e0de930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:32.604488Z","signature_b64":"QX16j+YJCbPCDxEmoflwZma7h/OGT4JsprUisuLEm6AIFGB2Vwn6IR+O+3Y08KP88h+hoLaJtIGNx661JzAaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c7e676be3f00df7ef3efb9d113bc5e0631b9ffa52bddd9a3c6772340caffe7f","last_reissued_at":"2026-07-05T10:14:32.603947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:32.603947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan Bundy, Kwabena Nuamah, Liane Guillou, Nick Ferguson","submitted_at":"2025-02-14T17:55:43Z","abstract_excerpt":"Large Language Models (LLMs) excel in natural language tasks but still face challenges in Question Answering (QA) tasks requiring complex, multi-step reasoning. We outline the types of reasoning required in some of these tasks, and reframe them in terms of meta-level reasoning (akin to high-level strategic reasoning or planning) and object-level reasoning (embodied in lower-level tasks such as mathematical reasoning). Franklin, a novel dataset with requirements of meta- and object-level reasoning, is introduced and used along with three other datasets to evaluate four LLMs at question answerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10338","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/2502.10338/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":"2502.10338","created_at":"2026-07-05T10:14:32.604018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10338v1","created_at":"2026-07-05T10:14:32.604018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10338","created_at":"2026-07-05T10:14:32.604018+00:00"},{"alias_kind":"pith_short_12","alias_value":"JR7GO27D6AG7","created_at":"2026-07-05T10:14:32.604018+00:00"},{"alias_kind":"pith_short_16","alias_value":"JR7GO27D6AG7P3Z6","created_at":"2026-07-05T10:14:32.604018+00:00"},{"alias_kind":"pith_short_8","alias_value":"JR7GO27D","created_at":"2026-07-05T10:14:32.604018+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/JR7GO27D6AG7P3Z67OORCO6F4B","json":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B.json","graph_json":"https://pith.science/api/pith-number/JR7GO27D6AG7P3Z67OORCO6F4B/graph.json","events_json":"https://pith.science/api/pith-number/JR7GO27D6AG7P3Z67OORCO6F4B/events.json","paper":"https://pith.science/paper/JR7GO27D"},"agent_actions":{"view_html":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B","download_json":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B.json","view_paper":"https://pith.science/paper/JR7GO27D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10338&json=true","fetch_graph":"https://pith.science/api/pith-number/JR7GO27D6AG7P3Z67OORCO6F4B/graph.json","fetch_events":"https://pith.science/api/pith-number/JR7GO27D6AG7P3Z67OORCO6F4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B/action/storage_attestation","attest_author":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B/action/author_attestation","sign_citation":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B/action/citation_signature","submit_replication":"https://pith.science/pith/JR7GO27D6AG7P3Z67OORCO6F4B/action/replication_record"}},"created_at":"2026-07-05T10:14:32.604018+00:00","updated_at":"2026-07-05T10:14:32.604018+00:00"}