{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6ESMROJMVG33HH5S5ZB2PUZ57Y","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":"d3bc3aa72d96eb1d0720a95dd1db140cd5f83c1ae0268b2151a5da93ce19ed35","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-06T07:10:25Z","title_canon_sha256":"20ce601ffb35df96f1f6dd2098a492386e49d1ae29a0ec37d7838b92530918df"},"schema_version":"1.0","source":{"id":"2606.08015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08015","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08015v1","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08015","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"6ESMROJMVG33","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"6ESMROJMVG33HH5S","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"6ESMROJM","created_at":"2026-06-09T01:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:ab3a6168a31a1707704d9db7c934fba0df215d0d97c854f5f21a1c72d62d734c","target":"graph","created_at":"2026-06-09T01:05:22Z","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/2606.08015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Q-Guided Value-Gradient Matching (Q-VGM), an off-policy reinforcement learning (RL) method that tackles a long-standing challenge in fine-tuning flow-matching vision-language-action (VLA) policies: efficiently improving an expressive flow-matching action expert with respect to a learned Q-function. Effective improvement must exploit the first-order (gradient) information of the critic, but this is difficult for flow policies, because directly back-propagating the value through their multi-step denoising process is numerically unstable at VLA scale, while the tractable action likelih","authors_text":"Jiayu Sun, Minqian Wang, Xingjian Mao, Yao Mu, Ziqian Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-06T07:10:25Z","title":"Q-VGM: Q-Guided Value-Gradient Matching for Flow-Matching VLA Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08015","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":"sha256:5640e34a65528657daad8d5c3bc0b5211438e952cd62265f96d51142ae2bed30","target":"record","created_at":"2026-06-09T01:05:22Z","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":"d3bc3aa72d96eb1d0720a95dd1db140cd5f83c1ae0268b2151a5da93ce19ed35","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-06T07:10:25Z","title_canon_sha256":"20ce601ffb35df96f1f6dd2098a492386e49d1ae29a0ec37d7838b92530918df"},"schema_version":"1.0","source":{"id":"2606.08015","kind":"arxiv","version":1}},"canonical_sha256":"f124c8b92ca9b7b39fb2ee43a7d33dfe037397d91b7fca0e6439a7e26feb536c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f124c8b92ca9b7b39fb2ee43a7d33dfe037397d91b7fca0e6439a7e26feb536c","first_computed_at":"2026-06-09T01:05:22.822521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:22.822521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1v9thzynZrjCuYsVR14QGW9T1A+hXr31EzWzabOFWAeHzWWNs7ApPPP59a5uW7sG991wDWdlIrMLN5UL2l+YAg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:22.823286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5640e34a65528657daad8d5c3bc0b5211438e952cd62265f96d51142ae2bed30","sha256:ab3a6168a31a1707704d9db7c934fba0df215d0d97c854f5f21a1c72d62d734c"],"state_sha256":"0889c7078ebae2547a1fec5a6de502d266279b73d15cb39a85bbae883c0c1e7c"}