{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ARR72KYUPLZDZRZV6KUHGTCHNH","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":"bd026742da865e7984c4385363c9c8f331f45ca3ca4c763c5dface219a15c587","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:28:43Z","title_canon_sha256":"215b7decb953b9745084fe54061a32feb4a5d18bd4e3d01d705ae57e33a99e62"},"schema_version":"1.0","source":{"id":"2605.27079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27079","created_at":"2026-05-27T01:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27079v1","created_at":"2026-05-27T01:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27079","created_at":"2026-05-27T01:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"ARR72KYUPLZD","created_at":"2026-05-27T01:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"ARR72KYUPLZDZRZV","created_at":"2026-05-27T01:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"ARR72KYU","created_at":"2026-05-27T01:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:a2da5353d334ca54ca2f4de939de734d49f910e9a781d863f57844804bc4e1b1","target":"graph","created_at":"2026-05-27T01:06:27Z","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/2605.27079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-learning with Adjoint Matching (QAM) addressed this issue by reformulating into a memoryless stochastic optimal control (SOC) problem with a learned critic. However, QAM inherits a fundamental fragility of critic-guided improvement: small critic errors are amplified when critics are ill-conditioned, often leading to model collapse. This paper introduces Trust Region Q-Adjoint Matching (TRQAM), a stable off-policy fine","authors_text":"Changyeon Kim, Jaehyuk Kim, Jinwoo Shin, Kyungmin Lee, Yonghoon Dong","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:28:43Z","title":"Trust Region Q Adjoint Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27079","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":"sha256:51382c68a40bee26792db17fbb5949ca9f70411adccde445131003405eb2d5f8","target":"record","created_at":"2026-05-27T01:06:27Z","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":"bd026742da865e7984c4385363c9c8f331f45ca3ca4c763c5dface219a15c587","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:28:43Z","title_canon_sha256":"215b7decb953b9745084fe54061a32feb4a5d18bd4e3d01d705ae57e33a99e62"},"schema_version":"1.0","source":{"id":"2605.27079","kind":"arxiv","version":1}},"canonical_sha256":"0463fd2b147af23cc735f2a8734c4769dd8f723a225fa81ddaba517dbe122c18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0463fd2b147af23cc735f2a8734c4769dd8f723a225fa81ddaba517dbe122c18","first_computed_at":"2026-05-27T01:06:27.247025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:27.247025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kBEiIro9BMNrWTgE6aJinFY2yTYTIwxdYmAvJ3i6ijlZFc4Wzz/5zKZtAMjOcNcAOdiUYMLoFQDkD+HLc1tbCA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:27.247491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51382c68a40bee26792db17fbb5949ca9f70411adccde445131003405eb2d5f8","sha256:a2da5353d334ca54ca2f4de939de734d49f910e9a781d863f57844804bc4e1b1"],"state_sha256":"5c1a6c2c4bfb8f54dace46d0a0abc5e09df3d65ebedf5a47f50ab19c5e9d134c"}