{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QFFGEDBSEWE5MYE6SB4FEWHTND","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":"a6c58b333ab86484e6f3b391e5ffa919d41a387ddec7b72760dcbc66b21182de","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T17:10:39Z","title_canon_sha256":"8b4c9c7701d86d7b8fdef10d0de9ad5d5e3a8354d0b0fe39df53fa5ca7ab8e28"},"schema_version":"1.0","source":{"id":"2410.18921","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18921","created_at":"2026-07-05T10:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18921v2","created_at":"2026-07-05T10:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18921","created_at":"2026-07-05T10:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"QFFGEDBSEWE5","created_at":"2026-07-05T10:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"QFFGEDBSEWE5MYE6","created_at":"2026-07-05T10:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"QFFGEDBS","created_at":"2026-07-05T10:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:d86ada735e6aa64f44996bc6f03fcbf9765f55aeeb8787de5913c22799e234ec","target":"graph","created_at":"2026-07-05T10:44:40Z","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/2410.18921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider the math problem: \"Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily have now?\" Many large language models (LLMs) in previous research approach this problem by calculating the answer \"1\" using the equation \"3 - 5 + 3.\" However, from a human perspective, we recognize the inherent flaw in this problem: Lily cannot eat 5 cookies if she initially only had 3. This discrepancy prompts a key question: Are current LLMs merely Blind Solver that apply mathematical operations without deeper reason","authors_text":"A M Muntasir Rahman, Guiling Wang, Jesse Yu, Jonathan Yu, Junyi Ye, Sierra S. Liu, Wei Yao, Wenpeng Yin","cross_cats":["cs.AI","cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T17:10:39Z","title":"From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18921","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":"sha256:4579caf6e0797591bc3747016ee7af8cc1be22327fcd4c635f2e30a06ccfbea7","target":"record","created_at":"2026-07-05T10:44:40Z","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":"a6c58b333ab86484e6f3b391e5ffa919d41a387ddec7b72760dcbc66b21182de","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T17:10:39Z","title_canon_sha256":"8b4c9c7701d86d7b8fdef10d0de9ad5d5e3a8354d0b0fe39df53fa5ca7ab8e28"},"schema_version":"1.0","source":{"id":"2410.18921","kind":"arxiv","version":2}},"canonical_sha256":"814a620c322589d6609e90785258f368f00a8ad8aee9111c9616e44f0bb33e0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814a620c322589d6609e90785258f368f00a8ad8aee9111c9616e44f0bb33e0e","first_computed_at":"2026-07-05T10:44:40.872173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:40.872173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xM3BjgxtdlpIie9dLseboMB4DJ56mPiIlPSxlq0xO1eu/oOIoWefKJ8k37Ko2vKoTsoVlNKVueIAEjIwgqt5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:40.872666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18921","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4579caf6e0797591bc3747016ee7af8cc1be22327fcd4c635f2e30a06ccfbea7","sha256:d86ada735e6aa64f44996bc6f03fcbf9765f55aeeb8787de5913c22799e234ec"],"state_sha256":"57e0798ea549627e38c719c3aed9615b9049eb5cd5185f0c4ca2507c15ec1f3a"}