{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SECL6KFTHS2IS362PX6IHWJDY7","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":"92fe04cfbb3376f3df04dd14495c90af794eafdce00bed1ab0f72caa916602a8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T09:12:12Z","title_canon_sha256":"2ab45083bf5f830971a5a54e68361867c52665f3b1336ce0ecefe56e30e64997"},"schema_version":"1.0","source":{"id":"2606.10613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10613","created_at":"2026-06-10T01:10:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10613v1","created_at":"2026-06-10T01:10:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10613","created_at":"2026-06-10T01:10:29Z"},{"alias_kind":"pith_short_12","alias_value":"SECL6KFTHS2I","created_at":"2026-06-10T01:10:29Z"},{"alias_kind":"pith_short_16","alias_value":"SECL6KFTHS2IS362","created_at":"2026-06-10T01:10:29Z"},{"alias_kind":"pith_short_8","alias_value":"SECL6KFT","created_at":"2026-06-10T01:10:29Z"}],"graph_snapshots":[{"event_id":"sha256:44d595ec6a9ff6a149467b9d9e525b6cad2519248f269821edf5d4a1aa74a3b2","target":"graph","created_at":"2026-06-10T01:10:29Z","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/2606.10613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based Q-learning has emerged as a powerful paradigm for offline reinforcement learning, but its reliance on multi-step denoising makes both training and inference computationally expensive and brittle. Recent efforts to accelerate diffusion Q-learning toward single-step action generation typically introduce auxiliary networks, policy distillation, or multi-phase training, which frequently compromise simplicity, stability, or performance. To address these limitations, we introduce Bootstrapped Flow Q-Learning (BFQ), a novel framework that enables accurate single-step action generation","authors_text":"Chang D. Yoo, Hongbin Choe, Thanh Nguyen, Tri Ton, Tung M. Luu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T09:12:12Z","title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10613","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:a3272c13eefe596153895ff024c0d90b197b8e6309c17cce79f454f1da8f3bd4","target":"record","created_at":"2026-06-10T01:10:29Z","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":"92fe04cfbb3376f3df04dd14495c90af794eafdce00bed1ab0f72caa916602a8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T09:12:12Z","title_canon_sha256":"2ab45083bf5f830971a5a54e68361867c52665f3b1336ce0ecefe56e30e64997"},"schema_version":"1.0","source":{"id":"2606.10613","kind":"arxiv","version":1}},"canonical_sha256":"9104bf28b33cb4896fda7dfc83d923c7ddb04e57cb47007fc5a59ed308a54fac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9104bf28b33cb4896fda7dfc83d923c7ddb04e57cb47007fc5a59ed308a54fac","first_computed_at":"2026-06-10T01:10:29.501304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:29.501304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ub/VZnyXKHzPIAoW3k56G4PFOcrx//TKZTOiBYfBx1gQkqa0MUrrFOF0PNbQlcFm/TZ6VlkYpqwhO3+f7M10CA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:29.502161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3272c13eefe596153895ff024c0d90b197b8e6309c17cce79f454f1da8f3bd4","sha256:44d595ec6a9ff6a149467b9d9e525b6cad2519248f269821edf5d4a1aa74a3b2"],"state_sha256":"0c353cc65b524604d5b2f7cbd231f47b4ca2d5bcb12a897ae3b716cb8e9dc006"}