{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5HB33IRC4PAKWXICLI2NLTXKZ7","short_pith_number":"pith:5HB33IRC","schema_version":"1.0","canonical_sha256":"e9c3bda222e3c0ab5d025a34d5ceeacffbb6446c6e7df07556b276b1428aec27","source":{"kind":"arxiv","id":"2504.02354","version":3},"attestation_state":"computed","paper":{"title":"Improving turbulence control through explainable deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.flu-dyn","authors_text":"Andres Cremades, Luca Guastoni, Miguel Beneitez, Ricardo Vinuesa","submitted_at":"2025-04-03T07:42:47Z","abstract_excerpt":"Turbulent-flow control aims to develop strategies that effectively manipulate fluid systems, such as the reduction of drag in transportation and enhancing energy efficiency, both critical steps towards reducing global CO$_2$ emissions. Deep reinforcement learning (DRL) offers novel tools to discover flow-control strategies, which we combine with our knowledge of the physics of turbulence. We integrate explainable deep learning (XDL) to objectively identify the coherent structures containing the most informative regions in the flow, with a DRL model trained to reduce them. The model trained wit"},"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":"2504.02354","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.flu-dyn","submitted_at":"2025-04-03T07:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"72bc408168113a2b489f2c9bcca335ba27c7507ec83ab0e77d38137997e8fde8","abstract_canon_sha256":"c21b8a2be060bad32edb87a5c63381dff0e3935fec1c8136cb47a9e5bad1a7c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:06.872506Z","signature_b64":"rOBMUCe1VE9ZZlPHbT51T1X5C2iK/KAMTzVJnaqhjm4pY4pSew1BfmVtoH1/QOyPIcR2qnkVYnxmTQfGiWmLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9c3bda222e3c0ab5d025a34d5ceeacffbb6446c6e7df07556b276b1428aec27","last_reissued_at":"2026-05-25T02:02:06.871839Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:06.871839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving turbulence control through explainable deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.flu-dyn","authors_text":"Andres Cremades, Luca Guastoni, Miguel Beneitez, Ricardo Vinuesa","submitted_at":"2025-04-03T07:42:47Z","abstract_excerpt":"Turbulent-flow control aims to develop strategies that effectively manipulate fluid systems, such as the reduction of drag in transportation and enhancing energy efficiency, both critical steps towards reducing global CO$_2$ emissions. Deep reinforcement learning (DRL) offers novel tools to discover flow-control strategies, which we combine with our knowledge of the physics of turbulence. We integrate explainable deep learning (XDL) to objectively identify the coherent structures containing the most informative regions in the flow, with a DRL model trained to reduce them. The model trained wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02354","kind":"arxiv","version":3},"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/2504.02354/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":"2504.02354","created_at":"2026-05-25T02:02:06.871935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02354v3","created_at":"2026-05-25T02:02:06.871935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02354","created_at":"2026-05-25T02:02:06.871935+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HB33IRC4PAK","created_at":"2026-05-25T02:02:06.871935+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HB33IRC4PAKWXIC","created_at":"2026-05-25T02:02:06.871935+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HB33IRC","created_at":"2026-05-25T02:02:06.871935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2509.24965","citing_title":"VIVALDy: A Hybrid Generative Reduced-Order Model for Turbulent Flows, Applied to Vortex-Induced Vibrations","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14022","citing_title":"Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09434","citing_title":"Physics-guided surrogate learning enables zero-shot control of turbulent wings","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7","json":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7.json","graph_json":"https://pith.science/api/pith-number/5HB33IRC4PAKWXICLI2NLTXKZ7/graph.json","events_json":"https://pith.science/api/pith-number/5HB33IRC4PAKWXICLI2NLTXKZ7/events.json","paper":"https://pith.science/paper/5HB33IRC"},"agent_actions":{"view_html":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7","download_json":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7.json","view_paper":"https://pith.science/paper/5HB33IRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02354&json=true","fetch_graph":"https://pith.science/api/pith-number/5HB33IRC4PAKWXICLI2NLTXKZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/5HB33IRC4PAKWXICLI2NLTXKZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7/action/storage_attestation","attest_author":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7/action/author_attestation","sign_citation":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7/action/citation_signature","submit_replication":"https://pith.science/pith/5HB33IRC4PAKWXICLI2NLTXKZ7/action/replication_record"}},"created_at":"2026-05-25T02:02:06.871935+00:00","updated_at":"2026-05-25T02:02:06.871935+00:00"}