{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DD6VNJQLHDXYRU7VQEXIK6OWTQ","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":"5e4a995a18fdbb1830c20c8c110612217608287b47d72775f118d8db208e755b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T15:49:43Z","title_canon_sha256":"ce1fdca47f03919fc4461b69fa3bd0af8ac11db72da074894ac0af871af8bca7"},"schema_version":"1.0","source":{"id":"2312.17080","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17080","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17080v4","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17080","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"DD6VNJQLHDXY","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"DD6VNJQLHDXYRU7V","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"DD6VNJQL","created_at":"2026-07-05T08:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:c36b1bd8a15551f93083c6474a83b8e2e885f6715973cc5b1823017468a96ec4","target":"graph","created_at":"2026-07-05T08:27:24Z","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/2312.17080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce a novel evaluation paradigm for Large Language Models (LLMs) that compels them to transition from a traditional question-answering role, akin to a student, to a solution-scoring role, akin to a teacher. This paradigm, focusing on \"reasoning about reasoning,\" hence termed meta-reasoning, shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation that effectively distinguishes between the cognitive capabilities of different models. By applying this paradigm in the GSM8K dataset, we have developed ","authors_text":"Haiyun Jiang, Jiaya Jia, Pengguang Chen, Shu Liu, Zhongshen Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T15:49:43Z","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17080","kind":"arxiv","version":4},"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:b1001dc60f5e4559f51093f95de5d90a78af4af2a34c7d8b1171dfea097b05f3","target":"record","created_at":"2026-07-05T08:27:24Z","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":"5e4a995a18fdbb1830c20c8c110612217608287b47d72775f118d8db208e755b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T15:49:43Z","title_canon_sha256":"ce1fdca47f03919fc4461b69fa3bd0af8ac11db72da074894ac0af871af8bca7"},"schema_version":"1.0","source":{"id":"2312.17080","kind":"arxiv","version":4}},"canonical_sha256":"18fd56a60b38ef88d3f5812e8579d69c27c7af858d190180040d1927d0dae12f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18fd56a60b38ef88d3f5812e8579d69c27c7af858d190180040d1927d0dae12f","first_computed_at":"2026-07-05T08:27:24.228591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:24.228591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uKYYR4RNg9AZYKy1G377Tkt0lGGG/kGa8YaQUUC5zMRV6okRuO8MQUd0KspYNDeArHJDTET7ctksbbvNmhsxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:24.229053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17080","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1001dc60f5e4559f51093f95de5d90a78af4af2a34c7d8b1171dfea097b05f3","sha256:c36b1bd8a15551f93083c6474a83b8e2e885f6715973cc5b1823017468a96ec4"],"state_sha256":"98a1b33c1ed8f1385f0c361442bd9327609b2bd953d3b4299bc72801de1c2c4a"}