{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DD6VNJQLHDXYRU7VQEXIK6OWTQ","short_pith_number":"pith:DD6VNJQL","schema_version":"1.0","canonical_sha256":"18fd56a60b38ef88d3f5812e8579d69c27c7af858d190180040d1927d0dae12f","source":{"kind":"arxiv","id":"2312.17080","version":4},"attestation_state":"computed","paper":{"title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyun Jiang, Jiaya Jia, Pengguang Chen, Shu Liu, Zhongshen Zeng","submitted_at":"2023-12-28T15:49:43Z","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 "},"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":"2312.17080","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T15:49:43Z","cross_cats_sorted":[],"title_canon_sha256":"ce1fdca47f03919fc4461b69fa3bd0af8ac11db72da074894ac0af871af8bca7","abstract_canon_sha256":"5e4a995a18fdbb1830c20c8c110612217608287b47d72775f118d8db208e755b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:24.229053Z","signature_b64":"uKYYR4RNg9AZYKy1G377Tkt0lGGG/kGa8YaQUUC5zMRV6okRuO8MQUd0KspYNDeArHJDTET7ctksbbvNmhsxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18fd56a60b38ef88d3f5812e8579d69c27c7af858d190180040d1927d0dae12f","last_reissued_at":"2026-07-05T08:27:24.228591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:24.228591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyun Jiang, Jiaya Jia, Pengguang Chen, Shu Liu, Zhongshen Zeng","submitted_at":"2023-12-28T15:49:43Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17080","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/2312.17080/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":"2312.17080","created_at":"2026-07-05T08:27:24.228648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17080v4","created_at":"2026-07-05T08:27:24.228648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17080","created_at":"2026-07-05T08:27:24.228648+00:00"},{"alias_kind":"pith_short_12","alias_value":"DD6VNJQLHDXY","created_at":"2026-07-05T08:27:24.228648+00:00"},{"alias_kind":"pith_short_16","alias_value":"DD6VNJQLHDXYRU7V","created_at":"2026-07-05T08:27:24.228648+00:00"},{"alias_kind":"pith_short_8","alias_value":"DD6VNJQL","created_at":"2026-07-05T08:27:24.228648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02374","citing_title":"DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17282","citing_title":"MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ","json":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ.json","graph_json":"https://pith.science/api/pith-number/DD6VNJQLHDXYRU7VQEXIK6OWTQ/graph.json","events_json":"https://pith.science/api/pith-number/DD6VNJQLHDXYRU7VQEXIK6OWTQ/events.json","paper":"https://pith.science/paper/DD6VNJQL"},"agent_actions":{"view_html":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ","download_json":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ.json","view_paper":"https://pith.science/paper/DD6VNJQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17080&json=true","fetch_graph":"https://pith.science/api/pith-number/DD6VNJQLHDXYRU7VQEXIK6OWTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DD6VNJQLHDXYRU7VQEXIK6OWTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ/action/storage_attestation","attest_author":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ/action/author_attestation","sign_citation":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ/action/citation_signature","submit_replication":"https://pith.science/pith/DD6VNJQLHDXYRU7VQEXIK6OWTQ/action/replication_record"}},"created_at":"2026-07-05T08:27:24.228648+00:00","updated_at":"2026-07-05T08:27:24.228648+00:00"}