{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PNSVU4Q6ZB7TDBYRH5KNM6I5R3","short_pith_number":"pith:PNSVU4Q6","canonical_record":{"source":{"id":"2502.11574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T09:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"fdcc2bc744f5f316dbbd71e9adaf0020567f0528ba03bd729edb7834f2baa6c1","abstract_canon_sha256":"46aacc707165d16b1a9926c1ab3a10d163d1d8f6b9b3a6347f5e533c03fe021e"},"schema_version":"1.0"},"canonical_sha256":"7b655a721ec87f3187113f54d6791d8ef263cbca3ce26f7f456db3cec1839066","source":{"kind":"arxiv","id":"2502.11574","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11574","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11574v2","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11574","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"PNSVU4Q6ZB7T","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"PNSVU4Q6ZB7TDBYR","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"PNSVU4Q6","created_at":"2026-07-05T10:17:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PNSVU4Q6ZB7TDBYRH5KNM6I5R3","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T09:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"fdcc2bc744f5f316dbbd71e9adaf0020567f0528ba03bd729edb7834f2baa6c1","abstract_canon_sha256":"46aacc707165d16b1a9926c1ab3a10d163d1d8f6b9b3a6347f5e533c03fe021e"},"schema_version":"1.0"},"canonical_sha256":"7b655a721ec87f3187113f54d6791d8ef263cbca3ce26f7f456db3cec1839066","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:54.450219Z","signature_b64":"8zio13q0qxBGXzOfgRcJvLVJcPq8/ELfdNMfGhgNG2UsltG1BqUaO9ri7g52PTpZ4+q8+SsFcsACt5VNqvtAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b655a721ec87f3187113f54d6791d8ef263cbca3ce26f7f456db3cec1839066","last_reissued_at":"2026-07-05T10:17:54.449790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:54.449790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11574","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":"2026-07-05T10:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Lgl8p+BTVA9dTIxDdvMZHy0t3ssoiPSr8vMmjaMS/8puB+yYwfvqluymMfnI0CaIR04+ipxdP9jHJ9XPy9lCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:41:59.255912Z"},"content_sha256":"98698e5e933dfd873bb07f00d015d64be2358c46059ba8d1df37c1fbda7a83b0","schema_version":"1.0","event_id":"sha256:98698e5e933dfd873bb07f00d015d64be2358c46059ba8d1df37c1fbda7a83b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PNSVU4Q6ZB7TDBYRH5KNM6I5R3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models and Mathematical Reasoning Failures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Birger Moell, Johan Boye","submitted_at":"2025-02-17T09:07:32Z","abstract_excerpt":"This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. Unlike prior studies that focus solely on answer correctness, we rigorously analyze both final answers and solution steps to identify reasoning failures. Evaluating eight state-of-the-art models - including Mixtral, Llama, Gemini, GPT-4o, and OpenAI's o1 variants - we find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic, sometime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11574","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/2502.11574/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":"2026-07-05T10:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lz8sY6m2wVYDp7hviFvUVCTWIU08eQTQGvVSaHSloMVqDpAiIiK/ukzjtiRQloaEUzW98jSdvaiTGWQ0rEPfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:41:59.256989Z"},"content_sha256":"95a6c425d9dd7ee2b3c82d6a6dcaaeeb568bd469c2f1c7f58b542354aab2ba94","schema_version":"1.0","event_id":"sha256:95a6c425d9dd7ee2b3c82d6a6dcaaeeb568bd469c2f1c7f58b542354aab2ba94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3/bundle.json","state_url":"https://pith.science/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3/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":"2026-08-11T03:41:59Z","links":{"resolver":"https://pith.science/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3","bundle":"https://pith.science/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3/bundle.json","state":"https://pith.science/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNSVU4Q6ZB7TDBYRH5KNM6I5R3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PNSVU4Q6ZB7TDBYRH5KNM6I5R3","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":"46aacc707165d16b1a9926c1ab3a10d163d1d8f6b9b3a6347f5e533c03fe021e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T09:07:32Z","title_canon_sha256":"fdcc2bc744f5f316dbbd71e9adaf0020567f0528ba03bd729edb7834f2baa6c1"},"schema_version":"1.0","source":{"id":"2502.11574","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11574","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11574v2","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11574","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"PNSVU4Q6ZB7T","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"PNSVU4Q6ZB7TDBYR","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"PNSVU4Q6","created_at":"2026-07-05T10:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:95a6c425d9dd7ee2b3c82d6a6dcaaeeb568bd469c2f1c7f58b542354aab2ba94","target":"graph","created_at":"2026-07-05T10:17:54Z","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/2502.11574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. Unlike prior studies that focus solely on answer correctness, we rigorously analyze both final answers and solution steps to identify reasoning failures. Evaluating eight state-of-the-art models - including Mixtral, Llama, Gemini, GPT-4o, and OpenAI's o1 variants - we find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic, sometime","authors_text":"Birger Moell, Johan Boye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T09:07:32Z","title":"Large Language Models and Mathematical Reasoning Failures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11574","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":"sha256:98698e5e933dfd873bb07f00d015d64be2358c46059ba8d1df37c1fbda7a83b0","target":"record","created_at":"2026-07-05T10:17:54Z","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":"46aacc707165d16b1a9926c1ab3a10d163d1d8f6b9b3a6347f5e533c03fe021e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T09:07:32Z","title_canon_sha256":"fdcc2bc744f5f316dbbd71e9adaf0020567f0528ba03bd729edb7834f2baa6c1"},"schema_version":"1.0","source":{"id":"2502.11574","kind":"arxiv","version":2}},"canonical_sha256":"7b655a721ec87f3187113f54d6791d8ef263cbca3ce26f7f456db3cec1839066","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b655a721ec87f3187113f54d6791d8ef263cbca3ce26f7f456db3cec1839066","first_computed_at":"2026-07-05T10:17:54.449790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:54.449790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zio13q0qxBGXzOfgRcJvLVJcPq8/ELfdNMfGhgNG2UsltG1BqUaO9ri7g52PTpZ4+q8+SsFcsACt5VNqvtAAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:54.450219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11574","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98698e5e933dfd873bb07f00d015d64be2358c46059ba8d1df37c1fbda7a83b0","sha256:95a6c425d9dd7ee2b3c82d6a6dcaaeeb568bd469c2f1c7f58b542354aab2ba94"],"state_sha256":"ca5ea16bcaab06b2dbd8090cfc0327b8e12af180e9cfced22c18b91e769532da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fPjscqC/3yo3PdGxx8szuc0E7hXu1/KFaiaZvsBow6xOuG9sMOYBwl/6WVp5tXbr7xAsCwV1/o5U4Csqfs5CDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:41:59.265645Z","bundle_sha256":"d3638837d6597145659eeabf455eaca5769109046adf194a567adcab6a3a2881"}}