{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DL6IEZSHVHFPYA7PJAL7GSNE45","short_pith_number":"pith:DL6IEZSH","schema_version":"1.0","canonical_sha256":"1afc826647a9cafc03ef4817f349a4e74e0618cbf42ee0f611145d0f78bbced7","source":{"kind":"arxiv","id":"2505.14354","version":1},"attestation_state":"computed","paper":{"title":"WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chau Yuen, Jiancheng An, Li Wei, Mengbing Liu, M\\'erouane Debbah, Xin Li","submitted_at":"2025-05-20T13:38:10Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive results across a broad array of tasks, yet their capacity for complex, domain-specific mathematical reasoning-particularly in wireless communications-remains underexplored. In this work, we introduce WirelessMathBench, a novel benchmark specifically designed to evaluate LLMs on mathematical modeling challenges to wireless communications engineering. Our benchmark consists of 587 meticulously curated questions sourced from 40 state-of-the-art research papers, encompassing a diverse spectrum of tasks ranging from basic multiple-choice questio"},"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":"2505.14354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T13:38:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4c80f56d82f52af0fb1db42b3689dd3c5032c135491a15f2219f66e340dc7bda","abstract_canon_sha256":"261ef3c8a03b9e5099bc6ed96db212e49010d059a147668135be434d877bea0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:00.154058Z","signature_b64":"9XL+paomN9N643QazlNjSsBz3EY/y9H8jWtZgSkCFT9tRSaof9ZnC/A3CYOrx69Xvww2lDsShO7XFOcmArFQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1afc826647a9cafc03ef4817f349a4e74e0618cbf42ee0f611145d0f78bbced7","last_reissued_at":"2026-07-05T11:06:00.153589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:00.153589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chau Yuen, Jiancheng An, Li Wei, Mengbing Liu, M\\'erouane Debbah, Xin Li","submitted_at":"2025-05-20T13:38:10Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive results across a broad array of tasks, yet their capacity for complex, domain-specific mathematical reasoning-particularly in wireless communications-remains underexplored. In this work, we introduce WirelessMathBench, a novel benchmark specifically designed to evaluate LLMs on mathematical modeling challenges to wireless communications engineering. Our benchmark consists of 587 meticulously curated questions sourced from 40 state-of-the-art research papers, encompassing a diverse spectrum of tasks ranging from basic multiple-choice questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14354","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/2505.14354/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":"2505.14354","created_at":"2026-07-05T11:06:00.153644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14354v1","created_at":"2026-07-05T11:06:00.153644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14354","created_at":"2026-07-05T11:06:00.153644+00:00"},{"alias_kind":"pith_short_12","alias_value":"DL6IEZSHVHFP","created_at":"2026-07-05T11:06:00.153644+00:00"},{"alias_kind":"pith_short_16","alias_value":"DL6IEZSHVHFPYA7P","created_at":"2026-07-05T11:06:00.153644+00:00"},{"alias_kind":"pith_short_8","alias_value":"DL6IEZSH","created_at":"2026-07-05T11:06:00.153644+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/DL6IEZSHVHFPYA7PJAL7GSNE45","json":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45.json","graph_json":"https://pith.science/api/pith-number/DL6IEZSHVHFPYA7PJAL7GSNE45/graph.json","events_json":"https://pith.science/api/pith-number/DL6IEZSHVHFPYA7PJAL7GSNE45/events.json","paper":"https://pith.science/paper/DL6IEZSH"},"agent_actions":{"view_html":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45","download_json":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45.json","view_paper":"https://pith.science/paper/DL6IEZSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14354&json=true","fetch_graph":"https://pith.science/api/pith-number/DL6IEZSHVHFPYA7PJAL7GSNE45/graph.json","fetch_events":"https://pith.science/api/pith-number/DL6IEZSHVHFPYA7PJAL7GSNE45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45/action/storage_attestation","attest_author":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45/action/author_attestation","sign_citation":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45/action/citation_signature","submit_replication":"https://pith.science/pith/DL6IEZSHVHFPYA7PJAL7GSNE45/action/replication_record"}},"created_at":"2026-07-05T11:06:00.153644+00:00","updated_at":"2026-07-05T11:06:00.153644+00:00"}