{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4GCOYZFZKY4JLXFUMWNYUPBFWN","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":"a8f397e96a0c0d3d8285a62b1443bff8ac93e54d2daf9ee1ad6f8a26c51bcea0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T15:49:13Z","title_canon_sha256":"b2d63acda36d4a0cc8c3f5ad55d71f135467ab38106a1da22b98f7cffec9b052"},"schema_version":"1.0","source":{"id":"2605.31455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31455","created_at":"2026-06-01T02:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31455v1","created_at":"2026-06-01T02:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31455","created_at":"2026-06-01T02:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"4GCOYZFZKY4J","created_at":"2026-06-01T02:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"4GCOYZFZKY4JLXFU","created_at":"2026-06-01T02:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"4GCOYZFZ","created_at":"2026-06-01T02:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:62c1a6f33d2323bc02b0c1d1e11418e0af0a3e9a05dac983baec2971aa065f80","target":"graph","created_at":"2026-06-01T02:04:06Z","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/2605.31455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly deployed in multi-turn interactive settings where users or environments can iteratively provide lightweight feedback. Unfortunately, optimizing such behavior presents a sharp dilemma in practice: online reinforcement learning is able to effectively address multi-turn dynamics but is prohibitively expensive due to the cost of generating full correction trajectories at every update, whereas offline supervised fine-tuning (SFT) is efficient but suffers from distribution shift and behavioral collapse. To this end, we novelly propose DRIFT (Decoupled Rollouts ","authors_text":"Chengwei Qin, Jian Mu, Tianyi Lin, Yao Shu, Zhongxiang Dai","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T15:49:13Z","title":"DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31455","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":"sha256:54caaea85213eb77e49c821dc5179823b38b79d018a407c7ad2127779d4897db","target":"record","created_at":"2026-06-01T02:04:06Z","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":"a8f397e96a0c0d3d8285a62b1443bff8ac93e54d2daf9ee1ad6f8a26c51bcea0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T15:49:13Z","title_canon_sha256":"b2d63acda36d4a0cc8c3f5ad55d71f135467ab38106a1da22b98f7cffec9b052"},"schema_version":"1.0","source":{"id":"2605.31455","kind":"arxiv","version":1}},"canonical_sha256":"e184ec64b9563895dcb4659b8a3c25b35e1bdb80e2bc3882843768df484ec9a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e184ec64b9563895dcb4659b8a3c25b35e1bdb80e2bc3882843768df484ec9a2","first_computed_at":"2026-06-01T02:04:06.751600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:04:06.751600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PDxPG5G91rLNuVZUJwwLFy3WObxZDhl/QlZPpekOWhmOfGN0fWsVelnFmd16fYy38rmcD0z6CqSxJ1GV699iDQ==","signature_status":"signed_v1","signed_at":"2026-06-01T02:04:06.752471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54caaea85213eb77e49c821dc5179823b38b79d018a407c7ad2127779d4897db","sha256:62c1a6f33d2323bc02b0c1d1e11418e0af0a3e9a05dac983baec2971aa065f80"],"state_sha256":"f3fc2230216ef07e0a2fba30bbcb3956012d0ad08c0a50544d963602a0caeaa2"}