{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WVCFGPJ6OV5EUYO5V63ESGVNN","short_pith_number":"pith:3WVCFGPJ","schema_version":"1.0","canonical_sha256":"ddaa2299e9f3abd2530eed7db248d56b614a16f9a69c9871153dcb79d7210ee4","source":{"kind":"arxiv","id":"2509.10185","version":1},"attestation_state":"computed","paper":{"title":"Discovering Flow Separation Control Strategies in 3D Wings via Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"B. Font, I. Rodriguez, J. Rabault, O. Lehmkuhl, P. Su\\'arez, R. Montal\\`a, R. Vinuesa","submitted_at":"2025-09-12T12:25:51Z","abstract_excerpt":"In this work, deep reinforcement learning (DRL) is applied to active flow control (AFC) over a threedimensional SD7003 wing at a Reynolds number of Re = 60,000 and angle of attack of AoA = 14 degrees. In the uncontrolled baseline case, the flow exhibits massive separation and a fully turbulent wake. Using a GPU-accelerated CFD solver and multi-agent training, DRL discovers control strategies that enhance lift (79%), reduce drag (65%), and improve aerodynamic efficiency (408%). Flow visualizations confirm reattachment of the separated shear layer, demonstrating the potential of DRL for complex "},"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":"2509.10185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CE","submitted_at":"2025-09-12T12:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"9669f3fc1ee8bf672a4c212279f55c085e27ea3c89f0c9dc7b8450d9461c3433","abstract_canon_sha256":"7d787078dd640eb4ee1c9a5119522cbfe3cd527145e4541b0b75fe00131842ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:04.511275Z","signature_b64":"Z0yhHWF0VM9sfrQr5e5d+26vNSG0EejS6TMMxEHMZCu+25579uFFeoZXL/MXK6WQUKC8KncnV3oWJ1UE/vehBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddaa2299e9f3abd2530eed7db248d56b614a16f9a69c9871153dcb79d7210ee4","last_reissued_at":"2026-07-05T12:11:04.510762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:04.510762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Flow Separation Control Strategies in 3D Wings via Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"B. Font, I. Rodriguez, J. Rabault, O. Lehmkuhl, P. Su\\'arez, R. Montal\\`a, R. Vinuesa","submitted_at":"2025-09-12T12:25:51Z","abstract_excerpt":"In this work, deep reinforcement learning (DRL) is applied to active flow control (AFC) over a threedimensional SD7003 wing at a Reynolds number of Re = 60,000 and angle of attack of AoA = 14 degrees. In the uncontrolled baseline case, the flow exhibits massive separation and a fully turbulent wake. Using a GPU-accelerated CFD solver and multi-agent training, DRL discovers control strategies that enhance lift (79%), reduce drag (65%), and improve aerodynamic efficiency (408%). Flow visualizations confirm reattachment of the separated shear layer, demonstrating the potential of DRL for complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10185","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/2509.10185/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":"2509.10185","created_at":"2026-07-05T12:11:04.510823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10185v1","created_at":"2026-07-05T12:11:04.510823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10185","created_at":"2026-07-05T12:11:04.510823+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WVCFGPJ6OV5","created_at":"2026-07-05T12:11:04.510823+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WVCFGPJ6OV5EUYO","created_at":"2026-07-05T12:11:04.510823+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WVCFGPJ","created_at":"2026-07-05T12:11:04.510823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11981","citing_title":"High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN","json":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN.json","graph_json":"https://pith.science/api/pith-number/3WVCFGPJ6OV5EUYO5V63ESGVNN/graph.json","events_json":"https://pith.science/api/pith-number/3WVCFGPJ6OV5EUYO5V63ESGVNN/events.json","paper":"https://pith.science/paper/3WVCFGPJ"},"agent_actions":{"view_html":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN","download_json":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN.json","view_paper":"https://pith.science/paper/3WVCFGPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10185&json=true","fetch_graph":"https://pith.science/api/pith-number/3WVCFGPJ6OV5EUYO5V63ESGVNN/graph.json","fetch_events":"https://pith.science/api/pith-number/3WVCFGPJ6OV5EUYO5V63ESGVNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN/action/storage_attestation","attest_author":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN/action/author_attestation","sign_citation":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN/action/citation_signature","submit_replication":"https://pith.science/pith/3WVCFGPJ6OV5EUYO5V63ESGVNN/action/replication_record"}},"created_at":"2026-07-05T12:11:04.510823+00:00","updated_at":"2026-07-05T12:11:04.510823+00:00"}