{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KBARRU3CUIHESIDOJFNH6YHTDX","short_pith_number":"pith:KBARRU3C","canonical_record":{"source":{"id":"2402.19255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T15:26:14Z","cross_cats_sorted":[],"title_canon_sha256":"d6354b470898a55c4a08ee3bc759e0a8a1444e2703fb5193be0e7cec0232e280","abstract_canon_sha256":"2d9662637a171cbbd7a4cbc3438db773cb887ea649a2c54a55dbe064be8ca415"},"schema_version":"1.0"},"canonical_sha256":"504118d362a20e49206e495a7f60f31dd02e9be69476465efe76e89ec89418d0","source":{"kind":"arxiv","id":"2402.19255","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19255","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19255v2","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19255","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_12","alias_value":"KBARRU3CUIHE","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_16","alias_value":"KBARRU3CUIHESIDO","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_8","alias_value":"KBARRU3C","created_at":"2026-07-05T08:38:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KBARRU3CUIHESIDOJFNH6YHTDX","target":"record","payload":{"canonical_record":{"source":{"id":"2402.19255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T15:26:14Z","cross_cats_sorted":[],"title_canon_sha256":"d6354b470898a55c4a08ee3bc759e0a8a1444e2703fb5193be0e7cec0232e280","abstract_canon_sha256":"2d9662637a171cbbd7a4cbc3438db773cb887ea649a2c54a55dbe064be8ca415"},"schema_version":"1.0"},"canonical_sha256":"504118d362a20e49206e495a7f60f31dd02e9be69476465efe76e89ec89418d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:57.850984Z","signature_b64":"Q9nb+QvC6ipOngTpciXgC0ThHwewD3M/JitZMLPK5zSd8t8GSKuPCFc/t8m2rmFIb59TUILsvf7fuFURQ9g0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"504118d362a20e49206e495a7f60f31dd02e9be69476465efe76e89ec89418d0","last_reissued_at":"2026-07-05T08:38:57.850550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:57.850550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.19255","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:38:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdVUNEUGpMzNllwF1o+X4ic5Yr0x5emollyMRCBknARXud+2MZWHGps6SCh6IuyF0/BAudGZ1R6gKok0oLDhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:37:57.854916Z"},"content_sha256":"e4a918d5294a376064a803f691449eeb3c7056aa1826ea286033a0cb20a6a514","schema_version":"1.0","event_id":"sha256:e4a918d5294a376064a803f691449eeb3c7056aa1826ea286033a0cb20a6a514"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KBARRU3CUIHESIDOJFNH6YHTDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leyang Cui, Lingpeng Kong, Qintong Li, Wei Bi, Xueliang Zhao","submitted_at":"2024-02-29T15:26:14Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathematical knowledge or merely rely on shortcuts for mathematical reasoning. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs' math reasoning capability by testing a wide range of question variations. We introduce the adversarial grade school math (GS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19255","kind":"arxiv","version":2},"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/2402.19255/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":"2026-07-05T08:38:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q90nPAdY0eTRTvsjQgI/qN4Tk7Uzm5AwUrKmt5H21xwHPwNPj8zbs7EcregzOQh9EvfaVtdB66aVx3phirIRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:37:57.855851Z"},"content_sha256":"4e011845fb6d70168b54741ca288ffe5543696951884ed81c7c71a55bd3ab6b5","schema_version":"1.0","event_id":"sha256:4e011845fb6d70168b54741ca288ffe5543696951884ed81c7c71a55bd3ab6b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBARRU3CUIHESIDOJFNH6YHTDX/bundle.json","state_url":"https://pith.science/pith/KBARRU3CUIHESIDOJFNH6YHTDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBARRU3CUIHESIDOJFNH6YHTDX/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":"2026-08-06T17:37:57Z","links":{"resolver":"https://pith.science/pith/KBARRU3CUIHESIDOJFNH6YHTDX","bundle":"https://pith.science/pith/KBARRU3CUIHESIDOJFNH6YHTDX/bundle.json","state":"https://pith.science/pith/KBARRU3CUIHESIDOJFNH6YHTDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBARRU3CUIHESIDOJFNH6YHTDX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KBARRU3CUIHESIDOJFNH6YHTDX","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":"2d9662637a171cbbd7a4cbc3438db773cb887ea649a2c54a55dbe064be8ca415","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T15:26:14Z","title_canon_sha256":"d6354b470898a55c4a08ee3bc759e0a8a1444e2703fb5193be0e7cec0232e280"},"schema_version":"1.0","source":{"id":"2402.19255","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19255","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19255v2","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19255","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_12","alias_value":"KBARRU3CUIHE","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_16","alias_value":"KBARRU3CUIHESIDO","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_8","alias_value":"KBARRU3C","created_at":"2026-07-05T08:38:57Z"}],"graph_snapshots":[{"event_id":"sha256:4e011845fb6d70168b54741ca288ffe5543696951884ed81c7c71a55bd3ab6b5","target":"graph","created_at":"2026-07-05T08:38:57Z","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/2402.19255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathematical knowledge or merely rely on shortcuts for mathematical reasoning. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs' math reasoning capability by testing a wide range of question variations. We introduce the adversarial grade school math (GS","authors_text":"Leyang Cui, Lingpeng Kong, Qintong Li, Wei Bi, Xueliang Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T15:26:14Z","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19255","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:e4a918d5294a376064a803f691449eeb3c7056aa1826ea286033a0cb20a6a514","target":"record","created_at":"2026-07-05T08:38:57Z","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":"2d9662637a171cbbd7a4cbc3438db773cb887ea649a2c54a55dbe064be8ca415","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T15:26:14Z","title_canon_sha256":"d6354b470898a55c4a08ee3bc759e0a8a1444e2703fb5193be0e7cec0232e280"},"schema_version":"1.0","source":{"id":"2402.19255","kind":"arxiv","version":2}},"canonical_sha256":"504118d362a20e49206e495a7f60f31dd02e9be69476465efe76e89ec89418d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"504118d362a20e49206e495a7f60f31dd02e9be69476465efe76e89ec89418d0","first_computed_at":"2026-07-05T08:38:57.850550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:57.850550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q9nb+QvC6ipOngTpciXgC0ThHwewD3M/JitZMLPK5zSd8t8GSKuPCFc/t8m2rmFIb59TUILsvf7fuFURQ9g0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:57.850984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19255","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4a918d5294a376064a803f691449eeb3c7056aa1826ea286033a0cb20a6a514","sha256:4e011845fb6d70168b54741ca288ffe5543696951884ed81c7c71a55bd3ab6b5"],"state_sha256":"3c21493125a2c37c2e23f53530c0ec9558535f18da92a87701251fa5f7bef928"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrmkWYOMn7W40wgeoc5z6q74zRl/OG2+WhbUCZhl/3n+iW706p+scxGkXdawIh67rdMpaGybxuKoiCA9/FwQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:37:57.863956Z","bundle_sha256":"0538c6b02d3a0c76f75aacede6512d45986fd5853715fd81d1b6f19cda811389"}}