{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5B34R6YIEJA2T76RR2CM52BVG","short_pith_number":"pith:F5B34R6Y","schema_version":"1.0","canonical_sha256":"2f43be47d841120d4ffe8c74267741a9a0c365b809802ed70286fa556bdc29a4","source":{"kind":"arxiv","id":"2606.31025","version":1},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Zhu, Deepak Akhare, Jian-Xun Wang, Luning Sun, Timo Bremer, Xiantao Fan, Xin-Yang Liu","submitted_at":"2026-06-30T01:46:48Z","abstract_excerpt":"Active flow control is a fundamental application in engineering. Recent advances in deep reinforcement learning have made progress in this field. However, the classical online RL approaches require extensive real-time interactions with the high fidelity environment, while each sensor configuration change necessitates whole policy retraining. All these factors result in prohibitive computational costs for real-world applications. In this work, we propose a novel offline RL framework that addresses both challenges through data-driven policy extraction. We develop a sensor position-conditioned ar"},"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":"2606.31025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T01:46:48Z","cross_cats_sorted":[],"title_canon_sha256":"d72143460b9ad3efc9711506ec8ad5ff04ccaee14379e7af085dad6cd93d84d7","abstract_canon_sha256":"2215269e1486962dff24adb4c96baa6716821f952fd264ab6996449402ebca7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:26.658300Z","signature_b64":"gAsbGH0r8t7Rs24kjG+tbp6RRs3NdGhY0Sm+4qCXEO3xta01YAZ/aVKTeIdOzVp9FM8/Q7LvOmPsRZoiSiK9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f43be47d841120d4ffe8c74267741a9a0c365b809802ed70286fa556bdc29a4","last_reissued_at":"2026-07-01T01:17:26.657737Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:26.657737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Zhu, Deepak Akhare, Jian-Xun Wang, Luning Sun, Timo Bremer, Xiantao Fan, Xin-Yang Liu","submitted_at":"2026-06-30T01:46:48Z","abstract_excerpt":"Active flow control is a fundamental application in engineering. Recent advances in deep reinforcement learning have made progress in this field. However, the classical online RL approaches require extensive real-time interactions with the high fidelity environment, while each sensor configuration change necessitates whole policy retraining. All these factors result in prohibitive computational costs for real-world applications. In this work, we propose a novel offline RL framework that addresses both challenges through data-driven policy extraction. We develop a sensor position-conditioned ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31025","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/2606.31025/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":"2606.31025","created_at":"2026-07-01T01:17:26.657804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31025v1","created_at":"2026-07-01T01:17:26.657804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31025","created_at":"2026-07-01T01:17:26.657804+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5B34R6YIEJA","created_at":"2026-07-01T01:17:26.657804+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5B34R6YIEJA2T76","created_at":"2026-07-01T01:17:26.657804+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5B34R6Y","created_at":"2026-07-01T01:17:26.657804+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/F5B34R6YIEJA2T76RR2CM52BVG","json":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG.json","graph_json":"https://pith.science/api/pith-number/F5B34R6YIEJA2T76RR2CM52BVG/graph.json","events_json":"https://pith.science/api/pith-number/F5B34R6YIEJA2T76RR2CM52BVG/events.json","paper":"https://pith.science/paper/F5B34R6Y"},"agent_actions":{"view_html":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG","download_json":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG.json","view_paper":"https://pith.science/paper/F5B34R6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31025&json=true","fetch_graph":"https://pith.science/api/pith-number/F5B34R6YIEJA2T76RR2CM52BVG/graph.json","fetch_events":"https://pith.science/api/pith-number/F5B34R6YIEJA2T76RR2CM52BVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG/action/storage_attestation","attest_author":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG/action/author_attestation","sign_citation":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG/action/citation_signature","submit_replication":"https://pith.science/pith/F5B34R6YIEJA2T76RR2CM52BVG/action/replication_record"}},"created_at":"2026-07-01T01:17:26.657804+00:00","updated_at":"2026-07-01T01:17:26.657804+00:00"}