{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VQ6I373VWFOF6XFLLBA23I2VIY","short_pith_number":"pith:VQ6I373V","canonical_record":{"source":{"id":"2502.08680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:53:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fd9be6da1e65dba46bf8b3c43d86cb1c82e09b35d60c0ebdc2cc32208bc388cb","abstract_canon_sha256":"cf4268567fd87ac77e2d27523ea513de1c17c71f66dd60f82088bfefe143d87b"},"schema_version":"1.0"},"canonical_sha256":"ac3c8dff75b15c5f5cab5841ada355461cf6599844cdeafbef80587c57471970","source":{"kind":"arxiv","id":"2502.08680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08680","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08680v1","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08680","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"VQ6I373VWFOF","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"VQ6I373VWFOF6XFL","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"VQ6I373V","created_at":"2026-07-05T10:13:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VQ6I373VWFOF6XFLLBA23I2VIY","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:53:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fd9be6da1e65dba46bf8b3c43d86cb1c82e09b35d60c0ebdc2cc32208bc388cb","abstract_canon_sha256":"cf4268567fd87ac77e2d27523ea513de1c17c71f66dd60f82088bfefe143d87b"},"schema_version":"1.0"},"canonical_sha256":"ac3c8dff75b15c5f5cab5841ada355461cf6599844cdeafbef80587c57471970","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:28.429628Z","signature_b64":"ovliq94MWautVqcewPgstNVNgCbxV4/9gR2vtymdhVNyW+Nn7l5oF3iEqljg2FcOvPTggLvtDQERtEWvjgbKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac3c8dff75b15c5f5cab5841ada355461cf6599844cdeafbef80587c57471970","last_reissued_at":"2026-07-05T10:13:28.429148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:28.429148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08680","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fE+Ove2bavx2G8fklsrRWd/vGY432QU+CqdKHDBPdPb0mSP5Qg03hJqgVbYdWAAFQop561tl9w5eA8pcFbZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T03:24:38.951911Z"},"content_sha256":"d4b08b42ddfaaaf8989aad926a136bc9ce092ce6d481c21de491f88256858cd8","schema_version":"1.0","event_id":"sha256:d4b08b42ddfaaaf8989aad926a136bc9ce092ce6d481c21de491f88256858cd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VQ6I373VWFOF6XFLLBA23I2VIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Keith Ross, Minwu Kim, Safal Shrestha","submitted_at":"2025-02-12T09:53:10Z","abstract_excerpt":"Mathematical reasoning in Large Language Models (LLMs) is often evaluated using benchmarks with limited numerical ranges, failing to reflect real-world problem-solving across diverse scales. Furthermore, most existing evaluation methods only compare model outputs to ground-truth answers, obscuring insights into reasoning processes. To address these limitations, we introduce GSM-Ranges, a dataset generator derived from GSM8K that systematically perturbs numerical values in math problems to assess model robustness across varying numerical scales. Additionally, we propose a novel grading methodol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08680","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/2502.08680/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBSh02qKyERcIxRPFtRLXiYripv1JnCDuT7yGPEMr0bIXCRVktXDb6LgfsFrxPj/E5+/C1D6c1z/+qbDAclADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T03:24:38.952437Z"},"content_sha256":"663a4b13c253e3e40f226d1de13545c12302a37e197dafea5c18028d5a6f0b57","schema_version":"1.0","event_id":"sha256:663a4b13c253e3e40f226d1de13545c12302a37e197dafea5c18028d5a6f0b57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQ6I373VWFOF6XFLLBA23I2VIY/bundle.json","state_url":"https://pith.science/pith/VQ6I373VWFOF6XFLLBA23I2VIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQ6I373VWFOF6XFLLBA23I2VIY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T03:24:38Z","links":{"resolver":"https://pith.science/pith/VQ6I373VWFOF6XFLLBA23I2VIY","bundle":"https://pith.science/pith/VQ6I373VWFOF6XFLLBA23I2VIY/bundle.json","state":"https://pith.science/pith/VQ6I373VWFOF6XFLLBA23I2VIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQ6I373VWFOF6XFLLBA23I2VIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VQ6I373VWFOF6XFLLBA23I2VIY","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":"cf4268567fd87ac77e2d27523ea513de1c17c71f66dd60f82088bfefe143d87b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:53:10Z","title_canon_sha256":"fd9be6da1e65dba46bf8b3c43d86cb1c82e09b35d60c0ebdc2cc32208bc388cb"},"schema_version":"1.0","source":{"id":"2502.08680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08680","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08680v1","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08680","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"VQ6I373VWFOF","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"VQ6I373VWFOF6XFL","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"VQ6I373V","created_at":"2026-07-05T10:13:28Z"}],"graph_snapshots":[{"event_id":"sha256:663a4b13c253e3e40f226d1de13545c12302a37e197dafea5c18028d5a6f0b57","target":"graph","created_at":"2026-07-05T10:13:28Z","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/2502.08680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical reasoning in Large Language Models (LLMs) is often evaluated using benchmarks with limited numerical ranges, failing to reflect real-world problem-solving across diverse scales. Furthermore, most existing evaluation methods only compare model outputs to ground-truth answers, obscuring insights into reasoning processes. To address these limitations, we introduce GSM-Ranges, a dataset generator derived from GSM8K that systematically perturbs numerical values in math problems to assess model robustness across varying numerical scales. Additionally, we propose a novel grading methodol","authors_text":"Keith Ross, Minwu Kim, Safal Shrestha","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:53:10Z","title":"Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08680","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:d4b08b42ddfaaaf8989aad926a136bc9ce092ce6d481c21de491f88256858cd8","target":"record","created_at":"2026-07-05T10:13:28Z","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":"cf4268567fd87ac77e2d27523ea513de1c17c71f66dd60f82088bfefe143d87b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T09:53:10Z","title_canon_sha256":"fd9be6da1e65dba46bf8b3c43d86cb1c82e09b35d60c0ebdc2cc32208bc388cb"},"schema_version":"1.0","source":{"id":"2502.08680","kind":"arxiv","version":1}},"canonical_sha256":"ac3c8dff75b15c5f5cab5841ada355461cf6599844cdeafbef80587c57471970","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac3c8dff75b15c5f5cab5841ada355461cf6599844cdeafbef80587c57471970","first_computed_at":"2026-07-05T10:13:28.429148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:28.429148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ovliq94MWautVqcewPgstNVNgCbxV4/9gR2vtymdhVNyW+Nn7l5oF3iEqljg2FcOvPTggLvtDQERtEWvjgbKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:28.429628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4b08b42ddfaaaf8989aad926a136bc9ce092ce6d481c21de491f88256858cd8","sha256:663a4b13c253e3e40f226d1de13545c12302a37e197dafea5c18028d5a6f0b57"],"state_sha256":"8831b90956a9d506f29c5cc417f252cd89b79416baedfccde6229947a8944f19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ikycz4VTPn8CcEqwns+g1416ebKjvasTi73nVYu8nX1icDts3FVRRvIb3bNxKVa6JzaDVVhRdKThgZ/7DZXwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T03:24:38.957288Z","bundle_sha256":"051603f99ed431804025ba3ca56e6d764e882294da6d9931450cec4cf5733cfe"}}