{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KIXHE2AEHCRMQHRQ62ZKBOQDHO","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":"b9e6b967301fdc615d7f5b933530ed00104c04755509b1ba29ae33d093463c4e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","title_canon_sha256":"731cd04e118918629469a0ee2f36ac42ea177e931f11fcf00b0eb3df79fbf276"},"schema_version":"1.0","source":{"id":"2408.10839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10839","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10839v2","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10839","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"KIXHE2AEHCRM","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"KIXHE2AEHCRMQHRQ","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"KIXHE2AE","created_at":"2026-07-05T09:51:35Z"}],"graph_snapshots":[{"event_id":"sha256:74005399b3f4ee7a33c194f2ba006caf72364844069e3a54e3e9b86b1721645d","target":"graph","created_at":"2026-07-05T09:51:35Z","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/2408.10839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of Large Language Models (LLMs) in mathematical reasoning has become a cornerstone of related research, demonstrating the intelligence of these models and enabling potential practical applications through their advanced performance, such as in educational settings. Despite the variety of datasets and in-context learning algorithms designed to improve the ability of LLMs to automate mathematical problem solving, the lack of comprehensive benchmarking across different datasets makes it complicated to select an appropriate model for specific tasks. In this project, we present a benchmark ","authors_text":"Emek G\\\"ozl\\\"ukl\\\"u, Enkelejda Kasneci, Kathrin Se{\\ss}ler, Yao Rong","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","title":"Benchmarking Large Language Models for Math Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10839","kind":"arxiv","version":2},"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":"sha256:2dc1f7ff8c9b8a92adf7db8be6420a52e6f3b6cde8d6757251bebb08c79e891f","target":"record","created_at":"2026-07-05T09:51:35Z","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":"b9e6b967301fdc615d7f5b933530ed00104c04755509b1ba29ae33d093463c4e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","title_canon_sha256":"731cd04e118918629469a0ee2f36ac42ea177e931f11fcf00b0eb3df79fbf276"},"schema_version":"1.0","source":{"id":"2408.10839","kind":"arxiv","version":2}},"canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","first_computed_at":"2026-07-05T09:51:35.528133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:35.528133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EBle04dT60+mNA6w4iZnpV/+fu7hKqFFWlBfal0EBGFimYcWS1d0BaWU4Ij8W1xR5LcAiygfSH7cmnJ5Q6ogDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:35.528603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dc1f7ff8c9b8a92adf7db8be6420a52e6f3b6cde8d6757251bebb08c79e891f","sha256:74005399b3f4ee7a33c194f2ba006caf72364844069e3a54e3e9b86b1721645d"],"state_sha256":"18d5236e5be0fdbe4b591ff6891394f0f1280f89754efd860e7d5c863d13d968"}