{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SECL6KFTHS2IS362PX6IHWJDY7","short_pith_number":"pith:SECL6KFT","schema_version":"1.0","canonical_sha256":"9104bf28b33cb4896fda7dfc83d923c7ddb04e57cb47007fc5a59ed308a54fac","source":{"kind":"arxiv","id":"2606.10613","version":1},"attestation_state":"computed","paper":{"title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang D. Yoo, Hongbin Choe, Thanh Nguyen, Tri Ton, Tung M. Luu","submitted_at":"2026-06-09T09:12:12Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.10613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T09:12:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ab45083bf5f830971a5a54e68361867c52665f3b1336ce0ecefe56e30e64997","abstract_canon_sha256":"92fe04cfbb3376f3df04dd14495c90af794eafdce00bed1ab0f72caa916602a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:29.502161Z","signature_b64":"Ub/VZnyXKHzPIAoW3k56G4PFOcrx//TKZTOiBYfBx1gQkqa0MUrrFOF0PNbQlcFm/TZ6VlkYpqwhO3+f7M10CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9104bf28b33cb4896fda7dfc83d923c7ddb04e57cb47007fc5a59ed308a54fac","last_reissued_at":"2026-06-10T01:10:29.501304Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:29.501304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang D. Yoo, Hongbin Choe, Thanh Nguyen, Tri Ton, Tung M. Luu","submitted_at":"2026-06-09T09:12:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10613","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.10613/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.10613","created_at":"2026-06-10T01:10:29.501441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10613v1","created_at":"2026-06-10T01:10:29.501441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10613","created_at":"2026-06-10T01:10:29.501441+00:00"},{"alias_kind":"pith_short_12","alias_value":"SECL6KFTHS2I","created_at":"2026-06-10T01:10:29.501441+00:00"},{"alias_kind":"pith_short_16","alias_value":"SECL6KFTHS2IS362","created_at":"2026-06-10T01:10:29.501441+00:00"},{"alias_kind":"pith_short_8","alias_value":"SECL6KFT","created_at":"2026-06-10T01:10:29.501441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7","json":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7.json","graph_json":"https://pith.science/api/pith-number/SECL6KFTHS2IS362PX6IHWJDY7/graph.json","events_json":"https://pith.science/api/pith-number/SECL6KFTHS2IS362PX6IHWJDY7/events.json","paper":"https://pith.science/paper/SECL6KFT"},"agent_actions":{"view_html":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7","download_json":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7.json","view_paper":"https://pith.science/paper/SECL6KFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10613&json=true","fetch_graph":"https://pith.science/api/pith-number/SECL6KFTHS2IS362PX6IHWJDY7/graph.json","fetch_events":"https://pith.science/api/pith-number/SECL6KFTHS2IS362PX6IHWJDY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7/action/storage_attestation","attest_author":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7/action/author_attestation","sign_citation":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7/action/citation_signature","submit_replication":"https://pith.science/pith/SECL6KFTHS2IS362PX6IHWJDY7/action/replication_record"}},"created_at":"2026-06-10T01:10:29.501441+00:00","updated_at":"2026-06-10T01:10:29.501441+00:00"}