{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IOWNV3U6XJMVWDS2KYVYRI5XGN","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":"dc5990e14e62be5f06e28eb7adfd88b94c57f091f0f830051840ac228748c3ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T18:18:01Z","title_canon_sha256":"ba3fa7336b05389fd7dd63a425f55cbb46760043af45295b20c6745dd308bd66"},"schema_version":"1.0","source":{"id":"2505.14810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14810","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14810v2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14810","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"IOWNV3U6XJMV","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"IOWNV3U6XJMVWDS2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"IOWNV3U6","created_at":"2026-07-05T11:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:aa116b76de6cbf8b31d4ddaea8d5e8ecb59426e355d51e05d42dcea07d375c5e","target":"graph","created_at":"2026-07-05T11:09:14Z","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/2505.14810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural language instructions remains underexplored. In this work, we introduce MathIF, a dedicated benchmark for evaluating instruction-following in mathematical reasoning tasks. Our empirical analysis reveals a consistent tension between scaling up reasoning capacity and maintaining controllability, as models that reason more effectively often struggle to comply with us","authors_text":"Jiawei Gu, Tingchen Fu, Xiaoye Qu, Yafu Li, Yu Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T18:18:01Z","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14810","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":"sha256:402f4361f6c124fa8a98c801db19f469d40fce8a25d9f0f46822bbe115ffcea5","target":"record","created_at":"2026-07-05T11:09:14Z","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":"dc5990e14e62be5f06e28eb7adfd88b94c57f091f0f830051840ac228748c3ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T18:18:01Z","title_canon_sha256":"ba3fa7336b05389fd7dd63a425f55cbb46760043af45295b20c6745dd308bd66"},"schema_version":"1.0","source":{"id":"2505.14810","kind":"arxiv","version":2}},"canonical_sha256":"43acdaee9eba595b0e5a562b88a3b733733b7177d25e63d06c6e054f29f80ff5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43acdaee9eba595b0e5a562b88a3b733733b7177d25e63d06c6e054f29f80ff5","first_computed_at":"2026-07-05T11:09:14.449545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:14.449545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VxvXXx4ZOtt+kJ0YNEINQD/p46HyPnnggi4KabDcVPeXRNiDlaFHWD+LrYW31D+EHZ0OytYlhtNs8HTz3ikDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:14.449985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:402f4361f6c124fa8a98c801db19f469d40fce8a25d9f0f46822bbe115ffcea5","sha256:aa116b76de6cbf8b31d4ddaea8d5e8ecb59426e355d51e05d42dcea07d375c5e"],"state_sha256":"f109776ff784f6236bb375586bf5c965c34fcc98ad55ed049191c5d48a709b8b"}