{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OX7MJV5XQ7FOUFGDYTKNAE2CXW","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":"6a79668bd3bde71c4d8374d8d88aca4e1b22effffb5d1236861d24ade599143b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:10:17Z","title_canon_sha256":"006b4604d3bdfb86be8985f535abb3d95a6f01e0a91c3c202c7e31fe57553d56"},"schema_version":"1.0","source":{"id":"2505.13026","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13026","created_at":"2026-07-05T11:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13026v3","created_at":"2026-07-05T11:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13026","created_at":"2026-07-05T11:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"OX7MJV5XQ7FO","created_at":"2026-07-05T11:48:03Z"},{"alias_kind":"pith_short_16","alias_value":"OX7MJV5XQ7FOUFGD","created_at":"2026-07-05T11:48:03Z"},{"alias_kind":"pith_short_8","alias_value":"OX7MJV5X","created_at":"2026-07-05T11:48:03Z"}],"graph_snapshots":[{"event_id":"sha256:d94256bdffe509eb1a8f10e45c8a931fd6337d5bc8538fab144ac8c899f907b6","target":"graph","created_at":"2026-07-05T11:48:03Z","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/2505.13026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel at mathematical reasoning and logical problem-solving. The current popular training paradigms primarily use supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance the models' reasoning abilities. However, when using SFT or RL alone, there are respective challenges: SFT may suffer from overfitting, while RL is prone to mode collapse. The state-of-the-art methods have proposed hybrid training schemes. However, static switching faces challenges such as poor generalization across different tasks and high dependence on data quality. In response to","authors_text":"Erqu Qin, Fazhong Liu, Haojin Zhu, Harry Zheng, Jack Chen, Naruto Liu, Tian Dong, Xiao Wang, Yan Meng, Yuhan Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:10:17Z","title":"Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13026","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":"sha256:86d53b738410026f7c14e5b82830e46be4d4267e077b0253e574a7a00925b55c","target":"record","created_at":"2026-07-05T11:48:03Z","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":"6a79668bd3bde71c4d8374d8d88aca4e1b22effffb5d1236861d24ade599143b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:10:17Z","title_canon_sha256":"006b4604d3bdfb86be8985f535abb3d95a6f01e0a91c3c202c7e31fe57553d56"},"schema_version":"1.0","source":{"id":"2505.13026","kind":"arxiv","version":3}},"canonical_sha256":"75fec4d7b787caea14c3c4d4d01342bda56175b5def09f7d85f11038f7dcb85c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75fec4d7b787caea14c3c4d4d01342bda56175b5def09f7d85f11038f7dcb85c","first_computed_at":"2026-07-05T11:48:03.839497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:03.839497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ef+Bv8uI1LoMo9O5wQgO/Mj1w1h3kOQU/MQtTmSnG+7XaFrwVNsleRJTzDvNqnKMZyVmyND2HQ9Kcebvlr9EAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:03.840128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13026","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86d53b738410026f7c14e5b82830e46be4d4267e077b0253e574a7a00925b55c","sha256:d94256bdffe509eb1a8f10e45c8a931fd6337d5bc8538fab144ac8c899f907b6"],"state_sha256":"5acea124c8c9c34df4370a59c5dd0070259805e7ddfc97db99133387b21a7900"}