{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F2E762HS25FSIDYYI4O4EBHWLJ","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":"4c9fd57b966d90098e21a82c7ebfe43d48f11b85efbf57c017b78c6a9c13e95d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-31T21:06:39Z","title_canon_sha256":"dc2dbf0ed24805517ad06a694e504e868e978ad4baad2827e17f1368055563ab"},"schema_version":"1.0","source":{"id":"2504.00226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00226","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00226v1","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00226","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"F2E762HS25FS","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"F2E762HS25FSIDYY","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"F2E762HS","created_at":"2026-07-05T10:42:22Z"}],"graph_snapshots":[{"event_id":"sha256:d3d09d74eea15f64853d41c670f25fa03a622f3aa3bbb78f23f6f1c8d43af38a","target":"graph","created_at":"2026-07-05T10:42:22Z","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/2504.00226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An essential element of human mathematical reasoning is our number sense -- an abstract understanding of numbers and their relationships -- which allows us to solve problems involving vast number spaces using limited computational resources. Mathematical reasoning of Large Language Models (LLMs) is often tested on high-level problems (such as Olympiad challenges, geometry, word problems, and puzzles), but their low-level number sense remains less explored. We introduce \"Numberland,\" a 100-problem test to evaluate the numerical reasoning abilities of LLM-based agents. The tasks -- basic operati","authors_text":"Roussel Rahman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-31T21:06:39Z","title":"Large Language Models in Numberland: A Quick Test of Their Numerical Reasoning Abilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00226","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":"sha256:37fd2f7bc794605f3d5ef73f50b134819df4af8b66dd29ef045cf56157e79330","target":"record","created_at":"2026-07-05T10:42:22Z","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":"4c9fd57b966d90098e21a82c7ebfe43d48f11b85efbf57c017b78c6a9c13e95d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-31T21:06:39Z","title_canon_sha256":"dc2dbf0ed24805517ad06a694e504e868e978ad4baad2827e17f1368055563ab"},"schema_version":"1.0","source":{"id":"2504.00226","kind":"arxiv","version":1}},"canonical_sha256":"2e89ff68f2d74b240f18471dc204f65a59197f7c361d5b3111d937dea6f04e9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e89ff68f2d74b240f18471dc204f65a59197f7c361d5b3111d937dea6f04e9c","first_computed_at":"2026-07-05T10:42:22.067052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:22.067052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"thaY4lSDDvoailnc2lS3weAmjBlxBpX4kDnUJOclxg22Yup9K0En9TcxFQtR/e8oxOOnnxhLkBjpX1z7GnuoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:22.067457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37fd2f7bc794605f3d5ef73f50b134819df4af8b66dd29ef045cf56157e79330","sha256:d3d09d74eea15f64853d41c670f25fa03a622f3aa3bbb78f23f6f1c8d43af38a"],"state_sha256":"625a48111b2721fee89596d4dc141928fd255ee2ac4f3e6fc7a5730ea9360815"}