{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W3REE26YVOE7PLRKK6IGV2XNA6","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":"589493eb6ab5c3a18b5ca1064d927ff9e94fa3c8f1da8b827ae967fe834101f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:37:57Z","title_canon_sha256":"cb6308e19d5989c4975508c9df5f32cef9a0c31dc8fdfa7eef289b0eac4b8712"},"schema_version":"1.0","source":{"id":"2505.23701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23701","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23701v1","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23701","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"W3REE26YVOE7","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"W3REE26YVOE7PLRK","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"W3REE26Y","created_at":"2026-07-05T11:12:12Z"}],"graph_snapshots":[{"event_id":"sha256:5de2560dcf2445e86f68d3bb613c3430010d0362110c5e3da312ebe694b7f46d","target":"graph","created_at":"2026-07-05T11:12:12Z","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/2505.23701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Final-answer-based metrics are commonly used for evaluating large language models (LLMs) on math word problems, often taken as proxies for reasoning ability. However, such metrics conflate two distinct sub-skills: abstract formulation (capturing mathematical relationships using expressions) and arithmetic computation (executing the calculations). Through a disentangled evaluation on GSM8K and SVAMP, we find that the final-answer accuracy of Llama-3 and Qwen2.5 (1B-32B) without CoT is overwhelmingly bottlenecked by the arithmetic computation step and not by the abstract formulation step. Contra","authors_text":"Jackie Chi Kit Cheung, Leila Pishdad, Meng Cao, Yanshuai Cao, Ziling Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:37:57Z","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23701","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:f241a59eb63eef096b72cddcf3cf0a94dfaf182e3103229db72f114322eb3a76","target":"record","created_at":"2026-07-05T11:12:12Z","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":"589493eb6ab5c3a18b5ca1064d927ff9e94fa3c8f1da8b827ae967fe834101f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:37:57Z","title_canon_sha256":"cb6308e19d5989c4975508c9df5f32cef9a0c31dc8fdfa7eef289b0eac4b8712"},"schema_version":"1.0","source":{"id":"2505.23701","kind":"arxiv","version":1}},"canonical_sha256":"b6e2426bd8ab89f7ae2a57906aeaed07a9b197978e6912b99f5c66e78a4cc432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6e2426bd8ab89f7ae2a57906aeaed07a9b197978e6912b99f5c66e78a4cc432","first_computed_at":"2026-07-05T11:12:12.889099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:12.889099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yHnBfCGXDePxsxHqWXXpm3Fz3W0cxCYRn7sdcVThENsnypWjP0M+1DbjaasqDXLuvYFTzSBPucz8SJI/as7sDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:12.889576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f241a59eb63eef096b72cddcf3cf0a94dfaf182e3103229db72f114322eb3a76","sha256:5de2560dcf2445e86f68d3bb613c3430010d0362110c5e3da312ebe694b7f46d"],"state_sha256":"9699f36954a52d2fda3c2a0c21470d9c815e13a55a51395c692ab873ef7a5574"}