{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CURSZJINY3RG7CDNVI5XFU5NDO","short_pith_number":"pith:CURSZJIN","schema_version":"1.0","canonical_sha256":"15232ca50dc6e26f886daa3b72d3ad1b9b56951999876bdc322f58e9916e7da7","source":{"kind":"arxiv","id":"2407.05134","version":1},"attestation_state":"computed","paper":{"title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cho-Jui Hsieh, Kuei-Chun Kao, Ruochen Wang","submitted_at":"2024-07-06T17:01:04Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance in solving math problems, a hallmark of human intelligence. Despite high success rates on current benchmarks; however, these often feature simple problems with only one or two unknowns, which do not sufficiently challenge their reasoning capacities. This paper introduces a novel benchmark, BeyondX, designed to address these limitations by incorporating problems with multiple unknowns. Recognizing the challenges in proposing multi-unknown problems from scratch, we developed BeyondX using an innovative automated pipeline that "},"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":"2407.05134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-06T17:01:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6842abb1b83342b627a4b0517cb9b2c33cf10b97268c5c101095084eaf190525","abstract_canon_sha256":"25f5eb1c3dd09a1717c19cc199ff9cfdd1380202e81f5891d0303dfaad0f4493"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:46.436163Z","signature_b64":"mOd2WY7w2P/B8Qfs1bbawC9ea0mXWpBtEb5lX/LjQOICzl0vafQv0CSy4oJkRl8uUW/olOxSB9udhD9TzjR8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15232ca50dc6e26f886daa3b72d3ad1b9b56951999876bdc322f58e9916e7da7","last_reissued_at":"2026-07-05T09:36:46.435514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:46.435514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cho-Jui Hsieh, Kuei-Chun Kao, Ruochen Wang","submitted_at":"2024-07-06T17:01:04Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance in solving math problems, a hallmark of human intelligence. Despite high success rates on current benchmarks; however, these often feature simple problems with only one or two unknowns, which do not sufficiently challenge their reasoning capacities. This paper introduces a novel benchmark, BeyondX, designed to address these limitations by incorporating problems with multiple unknowns. Recognizing the challenges in proposing multi-unknown problems from scratch, we developed BeyondX using an innovative automated pipeline that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05134","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/2407.05134/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":"2407.05134","created_at":"2026-07-05T09:36:46.435640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05134v1","created_at":"2026-07-05T09:36:46.435640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05134","created_at":"2026-07-05T09:36:46.435640+00:00"},{"alias_kind":"pith_short_12","alias_value":"CURSZJINY3RG","created_at":"2026-07-05T09:36:46.435640+00:00"},{"alias_kind":"pith_short_16","alias_value":"CURSZJINY3RG7CDN","created_at":"2026-07-05T09:36:46.435640+00:00"},{"alias_kind":"pith_short_8","alias_value":"CURSZJIN","created_at":"2026-07-05T09:36:46.435640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08680","citing_title":"Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO","json":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO.json","graph_json":"https://pith.science/api/pith-number/CURSZJINY3RG7CDNVI5XFU5NDO/graph.json","events_json":"https://pith.science/api/pith-number/CURSZJINY3RG7CDNVI5XFU5NDO/events.json","paper":"https://pith.science/paper/CURSZJIN"},"agent_actions":{"view_html":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO","download_json":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO.json","view_paper":"https://pith.science/paper/CURSZJIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05134&json=true","fetch_graph":"https://pith.science/api/pith-number/CURSZJINY3RG7CDNVI5XFU5NDO/graph.json","fetch_events":"https://pith.science/api/pith-number/CURSZJINY3RG7CDNVI5XFU5NDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO/action/storage_attestation","attest_author":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO/action/author_attestation","sign_citation":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO/action/citation_signature","submit_replication":"https://pith.science/pith/CURSZJINY3RG7CDNVI5XFU5NDO/action/replication_record"}},"created_at":"2026-07-05T09:36:46.435640+00:00","updated_at":"2026-07-05T09:36:46.435640+00:00"}