{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QFFGEDBSEWE5MYE6SB4FEWHTND","short_pith_number":"pith:QFFGEDBS","schema_version":"1.0","canonical_sha256":"814a620c322589d6609e90785258f368f00a8ad8aee9111c9616e44f0bb33e0e","source":{"kind":"arxiv","id":"2410.18921","version":2},"attestation_state":"computed","paper":{"title":"From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.CL","authors_text":"A M Muntasir Rahman, Guiling Wang, Jesse Yu, Jonathan Yu, Junyi Ye, Sierra S. Liu, Wei Yao, Wenpeng Yin","submitted_at":"2024-10-24T17:10:39Z","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"},"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":"2410.18921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T17:10:39Z","cross_cats_sorted":["cs.AI","cs.LO"],"title_canon_sha256":"8b4c9c7701d86d7b8fdef10d0de9ad5d5e3a8354d0b0fe39df53fa5ca7ab8e28","abstract_canon_sha256":"a6c58b333ab86484e6f3b391e5ffa919d41a387ddec7b72760dcbc66b21182de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:40.872666Z","signature_b64":"xM3BjgxtdlpIie9dLseboMB4DJ56mPiIlPSxlq0xO1eu/oOIoWefKJ8k37Ko2vKoTsoVlNKVueIAEjIwgqt5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"814a620c322589d6609e90785258f368f00a8ad8aee9111c9616e44f0bb33e0e","last_reissued_at":"2026-07-05T10:44:40.872173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:40.872173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.CL","authors_text":"A M Muntasir Rahman, Guiling Wang, Jesse Yu, Jonathan Yu, Junyi Ye, Sierra S. Liu, Wei Yao, Wenpeng Yin","submitted_at":"2024-10-24T17:10:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18921","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/2410.18921/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":"2410.18921","created_at":"2026-07-05T10:44:40.872230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18921v2","created_at":"2026-07-05T10:44:40.872230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18921","created_at":"2026-07-05T10:44:40.872230+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFFGEDBSEWE5","created_at":"2026-07-05T10:44:40.872230+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFFGEDBSEWE5MYE6","created_at":"2026-07-05T10:44:40.872230+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFFGEDBS","created_at":"2026-07-05T10:44:40.872230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20544","citing_title":"The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND","json":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND.json","graph_json":"https://pith.science/api/pith-number/QFFGEDBSEWE5MYE6SB4FEWHTND/graph.json","events_json":"https://pith.science/api/pith-number/QFFGEDBSEWE5MYE6SB4FEWHTND/events.json","paper":"https://pith.science/paper/QFFGEDBS"},"agent_actions":{"view_html":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND","download_json":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND.json","view_paper":"https://pith.science/paper/QFFGEDBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18921&json=true","fetch_graph":"https://pith.science/api/pith-number/QFFGEDBSEWE5MYE6SB4FEWHTND/graph.json","fetch_events":"https://pith.science/api/pith-number/QFFGEDBSEWE5MYE6SB4FEWHTND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND/action/storage_attestation","attest_author":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND/action/author_attestation","sign_citation":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND/action/citation_signature","submit_replication":"https://pith.science/pith/QFFGEDBSEWE5MYE6SB4FEWHTND/action/replication_record"}},"created_at":"2026-07-05T10:44:40.872230+00:00","updated_at":"2026-07-05T10:44:40.872230+00:00"}