{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JR7GO27D6AG7P3Z67OORCO6F4B","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":"44576afbfb23a51a320d669e54de2b4016380cfda8fa8cb2c92b635b6e0de930","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:55:43Z","title_canon_sha256":"8628b968406f76fc1de6a4da6cdeea8dea090993eb4d708cb69752246441a7c8"},"schema_version":"1.0","source":{"id":"2502.10338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10338","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10338v1","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10338","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"JR7GO27D6AG7","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"JR7GO27D6AG7P3Z6","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"JR7GO27D","created_at":"2026-07-05T10:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:b9c2eba7c9d80f2ee1176031098e3b2d1a410edafe0f78f480cd7f42dd028278","target":"graph","created_at":"2026-07-05T10:14:32Z","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/2502.10338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Bundy, Kwabena Nuamah, Liane Guillou, Nick Ferguson","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:55:43Z","title":"Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10338","kind":"arxiv","version":1},"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":"sha256:89fa9c9949968e1781c527cc60260ea0bbbb25d3ebbbd649341ff87fc5145bab","target":"record","created_at":"2026-07-05T10:14:32Z","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":"44576afbfb23a51a320d669e54de2b4016380cfda8fa8cb2c92b635b6e0de930","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:55:43Z","title_canon_sha256":"8628b968406f76fc1de6a4da6cdeea8dea090993eb4d708cb69752246441a7c8"},"schema_version":"1.0","source":{"id":"2502.10338","kind":"arxiv","version":1}},"canonical_sha256":"4c7e676be3f00df7ef3efb9d113bc5e0631b9ffa52bddd9a3c6772340caffe7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c7e676be3f00df7ef3efb9d113bc5e0631b9ffa52bddd9a3c6772340caffe7f","first_computed_at":"2026-07-05T10:14:32.603947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:32.603947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QX16j+YJCbPCDxEmoflwZma7h/OGT4JsprUisuLEm6AIFGB2Vwn6IR+O+3Y08KP88h+hoLaJtIGNx661JzAaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:32.604488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89fa9c9949968e1781c527cc60260ea0bbbb25d3ebbbd649341ff87fc5145bab","sha256:b9c2eba7c9d80f2ee1176031098e3b2d1a410edafe0f78f480cd7f42dd028278"],"state_sha256":"f7b4e80db214a24d547d33988be4ded4ee49ed24dc3220d92ddcb9590b47ba4e"}