{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CURSZJINY3RG7CDNVI5XFU5NDO","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":"25f5eb1c3dd09a1717c19cc199ff9cfdd1380202e81f5891d0303dfaad0f4493","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-06T17:01:04Z","title_canon_sha256":"6842abb1b83342b627a4b0517cb9b2c33cf10b97268c5c101095084eaf190525"},"schema_version":"1.0","source":{"id":"2407.05134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05134","created_at":"2026-07-05T09:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05134v1","created_at":"2026-07-05T09:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05134","created_at":"2026-07-05T09:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"CURSZJINY3RG","created_at":"2026-07-05T09:36:46Z"},{"alias_kind":"pith_short_16","alias_value":"CURSZJINY3RG7CDN","created_at":"2026-07-05T09:36:46Z"},{"alias_kind":"pith_short_8","alias_value":"CURSZJIN","created_at":"2026-07-05T09:36:46Z"}],"graph_snapshots":[{"event_id":"sha256:5421a68ce38d020a45238f37ca65d7c0970762af5a62922034e446d25c49a8b6","target":"graph","created_at":"2026-07-05T09:36:46Z","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/2407.05134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Cho-Jui Hsieh, Kuei-Chun Kao, Ruochen Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-06T17:01:04Z","title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05134","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":"sha256:111e346da127862f833c261092819a6bf35cd316ffcd522a06d3cec23a85ece2","target":"record","created_at":"2026-07-05T09:36:46Z","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":"25f5eb1c3dd09a1717c19cc199ff9cfdd1380202e81f5891d0303dfaad0f4493","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-06T17:01:04Z","title_canon_sha256":"6842abb1b83342b627a4b0517cb9b2c33cf10b97268c5c101095084eaf190525"},"schema_version":"1.0","source":{"id":"2407.05134","kind":"arxiv","version":1}},"canonical_sha256":"15232ca50dc6e26f886daa3b72d3ad1b9b56951999876bdc322f58e9916e7da7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15232ca50dc6e26f886daa3b72d3ad1b9b56951999876bdc322f58e9916e7da7","first_computed_at":"2026-07-05T09:36:46.435514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:46.435514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mOd2WY7w2P/B8Qfs1bbawC9ea0mXWpBtEb5lX/LjQOICzl0vafQv0CSy4oJkRl8uUW/olOxSB9udhD9TzjR8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:46.436163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:111e346da127862f833c261092819a6bf35cd316ffcd522a06d3cec23a85ece2","sha256:5421a68ce38d020a45238f37ca65d7c0970762af5a62922034e446d25c49a8b6"],"state_sha256":"6c896f44ae44bdebe09392f5af9782b9953b37d2442a147434a6ea2a8e878e94"}