{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FTH5IUW2DGWMRV6DV2RCN7HHBN","short_pith_number":"pith:FTH5IUW2","schema_version":"1.0","canonical_sha256":"2ccfd452da19acc8d7c3aea226fce70b671c7cec4ed2577fc2f3ff9e211700bf","source":{"kind":"arxiv","id":"2410.04698","version":1},"attestation_state":"computed","paper":{"title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Caiming Xiong, Doyen Sahoo, Ee-Peng Lim, HanZe Dong, Lei Wang, Shan Dong, Yalu Wang, Yuhui Xu","submitted_at":"2024-10-07T02:30:07Z","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"},"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":"2410.04698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T02:30:07Z","cross_cats_sorted":[],"title_canon_sha256":"a77c184af28bed8d787b7539eab01897eb8a44af3541d2df067cdcebefb3597c","abstract_canon_sha256":"c1b1ed95b041e1d1187d0db7a02f0036c410bcfedd78a2d1b70b53c3b5a0dfe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:54.750499Z","signature_b64":"PptUc3e4+sCKW5AQYwYXt4w3n5RCieT7KlRSoLaO1dEkP6kGW2dBqN7+IgsxW2Ap+Fv8dyV47vrDxhuiVq/PBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ccfd452da19acc8d7c3aea226fce70b671c7cec4ed2577fc2f3ff9e211700bf","last_reissued_at":"2026-07-05T09:16:54.749945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:54.749945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Caiming Xiong, Doyen Sahoo, Ee-Peng Lim, HanZe Dong, Lei Wang, Shan Dong, Yalu Wang, Yuhui Xu","submitted_at":"2024-10-07T02:30:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04698","kind":"arxiv","version":1},"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/2410.04698/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":"2410.04698","created_at":"2026-07-05T09:16:54.750003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04698v1","created_at":"2026-07-05T09:16:54.750003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04698","created_at":"2026-07-05T09:16:54.750003+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTH5IUW2DGWM","created_at":"2026-07-05T09:16:54.750003+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTH5IUW2DGWMRV6D","created_at":"2026-07-05T09:16:54.750003+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTH5IUW2","created_at":"2026-07-05T09:16:54.750003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN","json":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN.json","graph_json":"https://pith.science/api/pith-number/FTH5IUW2DGWMRV6DV2RCN7HHBN/graph.json","events_json":"https://pith.science/api/pith-number/FTH5IUW2DGWMRV6DV2RCN7HHBN/events.json","paper":"https://pith.science/paper/FTH5IUW2"},"agent_actions":{"view_html":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN","download_json":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN.json","view_paper":"https://pith.science/paper/FTH5IUW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04698&json=true","fetch_graph":"https://pith.science/api/pith-number/FTH5IUW2DGWMRV6DV2RCN7HHBN/graph.json","fetch_events":"https://pith.science/api/pith-number/FTH5IUW2DGWMRV6DV2RCN7HHBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN/action/storage_attestation","attest_author":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN/action/author_attestation","sign_citation":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN/action/citation_signature","submit_replication":"https://pith.science/pith/FTH5IUW2DGWMRV6DV2RCN7HHBN/action/replication_record"}},"created_at":"2026-07-05T09:16:54.750003+00:00","updated_at":"2026-07-05T09:16:54.750003+00:00"}