{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HVA45OHYWBSNY7GF5MENJK4P5H","short_pith_number":"pith:HVA45OHY","schema_version":"1.0","canonical_sha256":"3d41ceb8f8b064dc7cc5eb08d4ab8fe9f353e9ad9e8d3549592929fa817c0d59","source":{"kind":"arxiv","id":"2502.12589","version":1},"attestation_state":"computed","paper":{"title":"RM-PoT: Reformulating Mathematical Problems and Solving via Program of Thoughts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Tang, Nengwu Wu, Shujun Peng, Xinhan Lin, Yang Hu, Yu Zhang","submitted_at":"2025-02-18T06:54:32Z","abstract_excerpt":"Recently, substantial advancements have been made in training language models to carry out step-by-step reasoning for solving intricate numerical reasoning tasks. Beyond the methods used to solve these problems, the structure and formulation of the problems themselves also play a crucial role in determining the performance of large language models. We observe that even small changes in the surface form of mathematical problems can have a profound impact on both the answer distribution and solve rate. This highlights the vulnerability of LLMs to surface-level variations, revealing its limited r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.12589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T06:54:32Z","cross_cats_sorted":[],"title_canon_sha256":"29f87aa682a71afc6b41bae822a19e9e85277d22245b17a1ef56151986568a09","abstract_canon_sha256":"47ea47b92ab49c27478797a1ff28e7562177c77c0f5f52ea19f47157288cb1c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:58.002942Z","signature_b64":"W8DJFQJYlaZvNk1DWcJ8iQd3eprhpBzpb0hJdQZe5Pvk4yNQxQqGuz5HWWB+hxffd3dbsExyqzDzs2Wi94jDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d41ceb8f8b064dc7cc5eb08d4ab8fe9f353e9ad9e8d3549592929fa817c0d59","last_reissued_at":"2026-07-05T10:15:58.002450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:58.002450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RM-PoT: Reformulating Mathematical Problems and Solving via Program of Thoughts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Tang, Nengwu Wu, Shujun Peng, Xinhan Lin, Yang Hu, Yu Zhang","submitted_at":"2025-02-18T06:54:32Z","abstract_excerpt":"Recently, substantial advancements have been made in training language models to carry out step-by-step reasoning for solving intricate numerical reasoning tasks. Beyond the methods used to solve these problems, the structure and formulation of the problems themselves also play a crucial role in determining the performance of large language models. We observe that even small changes in the surface form of mathematical problems can have a profound impact on both the answer distribution and solve rate. This highlights the vulnerability of LLMs to surface-level variations, revealing its limited r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12589","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.12589/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.12589","created_at":"2026-07-05T10:15:58.002504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12589v1","created_at":"2026-07-05T10:15:58.002504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12589","created_at":"2026-07-05T10:15:58.002504+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVA45OHYWBSN","created_at":"2026-07-05T10:15:58.002504+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVA45OHYWBSNY7GF","created_at":"2026-07-05T10:15:58.002504+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVA45OHY","created_at":"2026-07-05T10:15:58.002504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26644","citing_title":"When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H","json":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H.json","graph_json":"https://pith.science/api/pith-number/HVA45OHYWBSNY7GF5MENJK4P5H/graph.json","events_json":"https://pith.science/api/pith-number/HVA45OHYWBSNY7GF5MENJK4P5H/events.json","paper":"https://pith.science/paper/HVA45OHY"},"agent_actions":{"view_html":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H","download_json":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H.json","view_paper":"https://pith.science/paper/HVA45OHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12589&json=true","fetch_graph":"https://pith.science/api/pith-number/HVA45OHYWBSNY7GF5MENJK4P5H/graph.json","fetch_events":"https://pith.science/api/pith-number/HVA45OHYWBSNY7GF5MENJK4P5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H/action/storage_attestation","attest_author":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H/action/author_attestation","sign_citation":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H/action/citation_signature","submit_replication":"https://pith.science/pith/HVA45OHYWBSNY7GF5MENJK4P5H/action/replication_record"}},"created_at":"2026-07-05T10:15:58.002504+00:00","updated_at":"2026-07-05T10:15:58.002504+00:00"}