{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CQWJ3FH2J2O7EIRATRJYINP3ER","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":"f6e8c89ce4821097e7dce029baf751de40903aa41fd13442a4fd0aff40f733e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T17:10:36Z","title_canon_sha256":"c1833f753ecf744f4408d09b4bd64464ed60e0432a0e8831f2404b1d8566741a"},"schema_version":"1.0","source":{"id":"2506.09942","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09942","created_at":"2026-07-05T11:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09942v1","created_at":"2026-07-05T11:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09942","created_at":"2026-07-05T11:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"CQWJ3FH2J2O7","created_at":"2026-07-05T11:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"CQWJ3FH2J2O7EIRA","created_at":"2026-07-05T11:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"CQWJ3FH2","created_at":"2026-07-05T11:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:56b6ce33f9af0d3efbcc152643ff5660c4b1f2935e963941c75f37c520eb8771","target":"graph","created_at":"2026-07-05T11:19:59Z","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/2506.09942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. However, best practices for RL in instruction following remain underexplored. In this work, we explore the verification challenge in RL for instruction following and propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model (e.g., QwQ-32B). To support this approach, we construct a high-quality instruction-following dataset, VerInstruct, con","authors_text":"Bin Xu, Hao Peng, Juanzi Li, Lei Hou, Xiaozhi Wang, Yunjia Qi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T17:10:36Z","title":"VerIF: Verification Engineering for Reinforcement Learning in Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09942","kind":"arxiv","version":1},"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":"sha256:3d0658598c45234a7cdfd66780dd53f6d4c9b5e28ad845083ce01c46d4776e7b","target":"record","created_at":"2026-07-05T11:19:59Z","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":"f6e8c89ce4821097e7dce029baf751de40903aa41fd13442a4fd0aff40f733e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T17:10:36Z","title_canon_sha256":"c1833f753ecf744f4408d09b4bd64464ed60e0432a0e8831f2404b1d8566741a"},"schema_version":"1.0","source":{"id":"2506.09942","kind":"arxiv","version":1}},"canonical_sha256":"142c9d94fa4e9df222209c538435fb247e4599843ada450759fda078e26c6e27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142c9d94fa4e9df222209c538435fb247e4599843ada450759fda078e26c6e27","first_computed_at":"2026-07-05T11:19:59.305421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:59.305421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EAucjWjxnTEFkJzVDM1G28zQ7RiqC2OJ/nqCvz3SUKI7CvcFqgpiE1DWkroiZYVHeIHsEFqKmOMwzQLn69QvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:59.305894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09942","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d0658598c45234a7cdfd66780dd53f6d4c9b5e28ad845083ce01c46d4776e7b","sha256:56b6ce33f9af0d3efbcc152643ff5660c4b1f2935e963941c75f37c520eb8771"],"state_sha256":"5d1563f8c50e2402a65a92ffa2bd66f7408c341d8b4fe2de10e7fc9a403d0241"}