{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NEZFSLMXZ2OA2XPMOP2B572IEY","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":"593d375e918362f09f90f79c4c8080e46bc12c24259c692c1933de1530eaea3e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T19:31:52Z","title_canon_sha256":"5941d0068e84d849082f6180441f874cad508dfd3042b372321b90a53cb2650f"},"schema_version":"1.0","source":{"id":"2505.14852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14852","created_at":"2026-07-05T11:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14852v1","created_at":"2026-07-05T11:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14852","created_at":"2026-07-05T11:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"NEZFSLMXZ2OA","created_at":"2026-07-05T11:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"NEZFSLMXZ2OA2XPM","created_at":"2026-07-05T11:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"NEZFSLMX","created_at":"2026-07-05T11:06:36Z"}],"graph_snapshots":[{"event_id":"sha256:a1723d6a5f243495fb711606594d2ac5f29b095b31badb0bb872f473c2aa64e3","target":"graph","created_at":"2026-07-05T11:06:36Z","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/2505.14852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"EasyMath is a compact benchmark for practical math reasoning in small language models. It covers thirteen categories, from basic arithmetic and order of operations to word problems, algebraic expressions, edge cases, and omits specialist topics. We tested 23 models (14M to 4B parameters) using exact, numerical, and symbolic checks on free-form answers in a zero-shot setting. Accuracy rises with size and training, chain-of-thought adds modest gains, and consistency improves at scale.","authors_text":"Angelecia Frey, Drishya Karki, Michiel Kamphuis","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T19:31:52Z","title":"EasyMath: A 0-shot Math Benchmark for SLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14852","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":"sha256:6b1a5b3597711a49416452ffcc37ebc10173813a28d862806abe41de7bed0a67","target":"record","created_at":"2026-07-05T11:06:36Z","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":"593d375e918362f09f90f79c4c8080e46bc12c24259c692c1933de1530eaea3e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T19:31:52Z","title_canon_sha256":"5941d0068e84d849082f6180441f874cad508dfd3042b372321b90a53cb2650f"},"schema_version":"1.0","source":{"id":"2505.14852","kind":"arxiv","version":1}},"canonical_sha256":"6932592d97ce9c0d5dec73f41eff482613e38f92321f90bd25ceb5619886bacf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6932592d97ce9c0d5dec73f41eff482613e38f92321f90bd25ceb5619886bacf","first_computed_at":"2026-07-05T11:06:36.398086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:36.398086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dyJ6dCbarUfE824ycewWp9ACGs3xJ/841jZP9BB3jfZ6PQQaO4leSkJ5aVVjctY6p1jnK8jjObQ1TQ+iL8ezCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:36.398574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b1a5b3597711a49416452ffcc37ebc10173813a28d862806abe41de7bed0a67","sha256:a1723d6a5f243495fb711606594d2ac5f29b095b31badb0bb872f473c2aa64e3"],"state_sha256":"c831a757b33541586f48e9b09efbafddb190f67e4b02da1f13cf104f47edff2f"}