{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6RCXNNVGS4KKOCJAOLMZJTMK6N","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":"f3fa81671dda088bbd5fbffad53b36d10dbecf77832a93b790637b222dd076ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T11:42:18Z","title_canon_sha256":"d7c4d4d907b38ad9d200ce210dfd0d710e8d878e9f84362cb345bfc04298c4c4"},"schema_version":"1.0","source":{"id":"2401.11467","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11467","created_at":"2026-07-05T07:58:26Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11467v2","created_at":"2026-07-05T07:58:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11467","created_at":"2026-07-05T07:58:26Z"},{"alias_kind":"pith_short_12","alias_value":"6RCXNNVGS4KK","created_at":"2026-07-05T07:58:26Z"},{"alias_kind":"pith_short_16","alias_value":"6RCXNNVGS4KKOCJA","created_at":"2026-07-05T07:58:26Z"},{"alias_kind":"pith_short_8","alias_value":"6RCXNNVG","created_at":"2026-07-05T07:58:26Z"}],"graph_snapshots":[{"event_id":"sha256:bfcf02e079cbfd0062e21686a17a81b9d8697c515e70d421ceab1c3cdcb14c6e","target":"graph","created_at":"2026-07-05T07:58:26Z","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/2401.11467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \\textit{know} when to use CoT and whether those CoT are always necessary to answer the question. This paper shows that LLMs tend to generate redundant calculations and reasoning on a manually constructed math QA dataset, GSM8K-Zero. GSM8K-Zero is constructed such that the questions can be answered without any calculations, but LLMs, including Llama-2 models and Claude-2, tend to generate lengthy and unnecessary calculations to answer the ques","authors_text":"Cheng-Han Chiang, Hung-yi Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T11:42:18Z","title":"Over-Reasoning and Redundant Calculation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11467","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:d9049829c0e44e91b0d0986f1df85d804e4c7cf197b26d216b21e0020f95f921","target":"record","created_at":"2026-07-05T07:58:26Z","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":"f3fa81671dda088bbd5fbffad53b36d10dbecf77832a93b790637b222dd076ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T11:42:18Z","title_canon_sha256":"d7c4d4d907b38ad9d200ce210dfd0d710e8d878e9f84362cb345bfc04298c4c4"},"schema_version":"1.0","source":{"id":"2401.11467","kind":"arxiv","version":2}},"canonical_sha256":"f44576b6a69714a7092072d994cd8af358e3fea715022425e00dd771ea1f1f58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f44576b6a69714a7092072d994cd8af358e3fea715022425e00dd771ea1f1f58","first_computed_at":"2026-07-05T07:58:26.900535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:26.900535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nJolbqAMzigbE42zZBGDL+V3McHEYZAzRR8EPGIs4rt7kgP4ww4P6jIHvagqWZjAZ0CxwmIbYUpPsirUws13DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:26.901197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11467","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9049829c0e44e91b0d0986f1df85d804e4c7cf197b26d216b21e0020f95f921","sha256:bfcf02e079cbfd0062e21686a17a81b9d8697c515e70d421ceab1c3cdcb14c6e"],"state_sha256":"4ed67a565acf9e675b8e298466199b85edeafd67059b5e5143e5c7096e00ae9b"}