{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FTH5IUW2DGWMRV6DV2RCN7HHBN","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":"c1b1ed95b041e1d1187d0db7a02f0036c410bcfedd78a2d1b70b53c3b5a0dfe6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T02:30:07Z","title_canon_sha256":"a77c184af28bed8d787b7539eab01897eb8a44af3541d2df067cdcebefb3597c"},"schema_version":"1.0","source":{"id":"2410.04698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04698","created_at":"2026-07-05T09:16:54Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04698v1","created_at":"2026-07-05T09:16:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04698","created_at":"2026-07-05T09:16:54Z"},{"alias_kind":"pith_short_12","alias_value":"FTH5IUW2DGWM","created_at":"2026-07-05T09:16:54Z"},{"alias_kind":"pith_short_16","alias_value":"FTH5IUW2DGWMRV6D","created_at":"2026-07-05T09:16:54Z"},{"alias_kind":"pith_short_8","alias_value":"FTH5IUW2","created_at":"2026-07-05T09:16:54Z"}],"graph_snapshots":[{"event_id":"sha256:b5813ab363eb4aabb517e688dad250300f175ea18368a1bc64bda9bf6f47d1ab","target":"graph","created_at":"2026-07-05T09:16:54Z","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/2410.04698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks evaluating the mathematical reasoning abilities of LLMs over long contexts, which is crucial for LLMs' application in real-world scenarios. In this paper, we introduce MathHay, an automated benchmark designed to assess the long-context mathematical reasoning capabilities of LLMs. Unlike previous benchmarks like Needle in a Haystack, which focus primarily on inf","authors_text":"Amrita Saha, Caiming Xiong, Doyen Sahoo, Ee-Peng Lim, HanZe Dong, Lei Wang, Shan Dong, Yalu Wang, Yuhui Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T02:30:07Z","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04698","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":"sha256:448a21197f3484a9f86b4e565dd1fb598ea632521a89637b18d5369d30b4b625","target":"record","created_at":"2026-07-05T09:16:54Z","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":"c1b1ed95b041e1d1187d0db7a02f0036c410bcfedd78a2d1b70b53c3b5a0dfe6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T02:30:07Z","title_canon_sha256":"a77c184af28bed8d787b7539eab01897eb8a44af3541d2df067cdcebefb3597c"},"schema_version":"1.0","source":{"id":"2410.04698","kind":"arxiv","version":1}},"canonical_sha256":"2ccfd452da19acc8d7c3aea226fce70b671c7cec4ed2577fc2f3ff9e211700bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ccfd452da19acc8d7c3aea226fce70b671c7cec4ed2577fc2f3ff9e211700bf","first_computed_at":"2026-07-05T09:16:54.749945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:54.749945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PptUc3e4+sCKW5AQYwYXt4w3n5RCieT7KlRSoLaO1dEkP6kGW2dBqN7+IgsxW2Ap+Fv8dyV47vrDxhuiVq/PBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:54.750499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:448a21197f3484a9f86b4e565dd1fb598ea632521a89637b18d5369d30b4b625","sha256:b5813ab363eb4aabb517e688dad250300f175ea18368a1bc64bda9bf6f47d1ab"],"state_sha256":"fdff55afe202911c3225f37663387c00bd370843475d758ba92ed755003a5a80"}