{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CUUG3JOF7OUH3BZXF3JRYTLVTW","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":"cb9dfdbbdc508f72dc0784370d0d0192622ce989406172e923b98917eec5ffeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T16:36:00Z","title_canon_sha256":"bdf3c45c8d929aa509ee93928ee36a7e40e74e875ad49a8f35bb597d140bc507"},"schema_version":"1.0","source":{"id":"2505.11423","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11423","created_at":"2026-07-05T12:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11423v3","created_at":"2026-07-05T12:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11423","created_at":"2026-07-05T12:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"CUUG3JOF7OUH","created_at":"2026-07-05T12:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"CUUG3JOF7OUH3BZX","created_at":"2026-07-05T12:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"CUUG3JOF","created_at":"2026-07-05T12:02:46Z"}],"graph_snapshots":[{"event_id":"sha256:4ba71eab1536efb9a3a4dd122a48f7a9a07f187e224a2abc837cac2ee65dabb9","target":"graph","created_at":"2026-07-05T12:02:46Z","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/2505.11423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising and previously overlooked phenomenon: explicit CoT reasoning can significantly degrade instruction-following accuracy. Evaluating 15 models on two benchmarks: IFEval (with simple, rule-verifiable constraints) and ComplexBench (with complex, compositional constraints), we consistently observe performance drops when CoT prompting is applied. Through large-scal","authors_text":"Anurag Beniwal, Narayanan Sadagopan, Xiaomin Li, Xupeng Chen, Yingying Zhuang, Zhiwei Zhang, Zhou Yu, Ziji Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T16:36:00Z","title":"When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11423","kind":"arxiv","version":3},"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:bd556667c74090596a7d548e833ee5c4b42bba5f992bc37e8aade3316668a9ad","target":"record","created_at":"2026-07-05T12:02:46Z","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":"cb9dfdbbdc508f72dc0784370d0d0192622ce989406172e923b98917eec5ffeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T16:36:00Z","title_canon_sha256":"bdf3c45c8d929aa509ee93928ee36a7e40e74e875ad49a8f35bb597d140bc507"},"schema_version":"1.0","source":{"id":"2505.11423","kind":"arxiv","version":3}},"canonical_sha256":"15286da5c5fba87d87372ed31c4d759d85572845495cc4aacad4e826b7462829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15286da5c5fba87d87372ed31c4d759d85572845495cc4aacad4e826b7462829","first_computed_at":"2026-07-05T12:02:46.286273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:46.286273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QTew13WVsyLWCK/GiZXy8I+hsVlN6YPIaVAHWbBdB4H4O5FeQm1lTytmfJD7E/uHsisYG7UzkgJQwEVYZBNvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:46.286893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11423","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd556667c74090596a7d548e833ee5c4b42bba5f992bc37e8aade3316668a9ad","sha256:4ba71eab1536efb9a3a4dd122a48f7a9a07f187e224a2abc837cac2ee65dabb9"],"state_sha256":"a7ffc44ff1b9a14fbc40b0ff54276674b16909a8c7ceee881a80aece3ca83e73"}