{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J55TMW2YIBOK5WHKG5C2JHTQRW","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":"4941679f43c3a8866ea0886a0d87f84b47e93d087ef2721a4b773b60f5fd89f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T10:48:28Z","title_canon_sha256":"b1ebadad6f4f1b8edf59f4eededc539b26095d2379a91600a075a3461fca125a"},"schema_version":"1.0","source":{"id":"2502.11075","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11075","created_at":"2026-07-05T11:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11075v2","created_at":"2026-07-05T11:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11075","created_at":"2026-07-05T11:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"J55TMW2YIBOK","created_at":"2026-07-05T11:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"J55TMW2YIBOK5WHK","created_at":"2026-07-05T11:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"J55TMW2Y","created_at":"2026-07-05T11:14:53Z"}],"graph_snapshots":[{"event_id":"sha256:f90536c991a69711eb5412eb5fa5bd70ad063f12c0546c44bb428e57c9d870ce","target":"graph","created_at":"2026-07-05T11:14:53Z","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/2502.11075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in natural language processing tasks, such as text generation and semantic understanding. However, their performance on numerical reasoning tasks, such as basic arithmetic, numerical retrieval, and magnitude comparison, remains surprisingly poor. This gap arises from their reliance on surface-level statistical patterns rather than understanding numbers as continuous magnitudes. Existing benchmarks primarily focus on either linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical rea","authors_text":"Chen Jason Zhang, Darian Li, Fei Teng, Haoyang Li, Lei Chen, Luyu Qiu, Nicole Hu, Qing Li, Xuejia Chen, Yiming Li, Zhanchao Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T10:48:28Z","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11075","kind":"arxiv","version":2},"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:d4d5501a8a94104ec659b841d074446b97d11a5f95060c588cd70857c45917cd","target":"record","created_at":"2026-07-05T11:14:53Z","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":"4941679f43c3a8866ea0886a0d87f84b47e93d087ef2721a4b773b60f5fd89f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T10:48:28Z","title_canon_sha256":"b1ebadad6f4f1b8edf59f4eededc539b26095d2379a91600a075a3461fca125a"},"schema_version":"1.0","source":{"id":"2502.11075","kind":"arxiv","version":2}},"canonical_sha256":"4f7b365b58405caed8ea3745a49e708db8823bdce0878d318472e543bec17505","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f7b365b58405caed8ea3745a49e708db8823bdce0878d318472e543bec17505","first_computed_at":"2026-07-05T11:14:53.803544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:53.803544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4SiCyhLvN5VOhQV4ccX5djzEqc69l5O/4BIm7AJAirJYTJGduWIxO4glBC3TlPQZvVGufZZH3h6P2hD+P1ahBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:53.804002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11075","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4d5501a8a94104ec659b841d074446b97d11a5f95060c588cd70857c45917cd","sha256:f90536c991a69711eb5412eb5fa5bd70ad063f12c0546c44bb428e57c9d870ce"],"state_sha256":"8e0e34b8be025b37014acde398b020c35b62ff373309fa365e710df2d4e00226"}